BPEs

Bad at phonetic/​character-level tasks. Disappointingly, the issues that have been noticed with GPT-2-poetry’s disinclination to rhyme remain. GPT-3 rhymes reasonably well and often when appropriate, but the improvement is much smaller on rhyming than it is on pretty much everything else. Apparently it is easier for GPT-3 to learn things like arithmetic and spreadsheets than it is to learn how to rhyme. (DeepMind’s 280b-parameter Gopher model is considerably better than GPT-3, but also uses BPEs and also cannot write rhyming poetry⁠; GPT-NeoX-20B likewise struggles with un-formatted arithmetic) A similar issue comes with puns. Better, but not as much better as one would expect given the leap on many other capabilities. Trying to generate puns or rhymes, it seems like GPT-3 know extremely well what they are on an abstract level, and will appropriately manipulate words and attempt to make puns or rhymes (see the shoggoth-cat dialogue below for a particularly striking example), but the words it chooses just aren’t right on a phonetic basis. On the other hand, it’s not as if GPT-3 is unable to understand humor—it is a brilliant mimic with parodies, has a cutting wit for satire, and can generate one-liners easily like the “I have a joke” format (1⁠, 2) or Drake memes⁠, as long as they rely more on semantics than syntax.

BPEs ≠ characters! My suspicion here is that these, and perhaps other issues, is due to the lossy BPE encoding. GPT models do not see individual characters, but instead a larger chunk, called a byte-pair encoding (BPE); a byte-pair is a simple compression scheme where 50,257 word fragments or characters are chosen to try to minimize the encoding length on some arbitrary text corpus, so a particularly common word may get a unique BPE while a longer word will be encoded as 2 or 3 BPEs, and a completely novel word will be encoded letter BPE by letter BPE as a fallback. Hence, even if 2 words sound and are spelled similarly, they may be given totally different BPE encodings which don’t have a single BPE in common.¹⁴

If BPEs are the problem, then because the knowledge of phonetics is erased from the training data, GPT-3 cannot rhyme (anymore than you can color this piece of text as a synesthete sees it): there will be no clever prompt programming trick which suddenly makes it fluently rhyme, and scaling will deliver only minor improvements. Consistent with this thesis, many API users have tried hard to make GPT-3 rhyme, in part to prove me wrong about BPEs being the problem, and failed miserably: you may think you have gotten some rhyming, because GPT-3 has memorized some common rhymes, on the level of doggerel, but as soon as you try to get some novel rhymes or test it on specified words, the inability is clear.

The pervasive use of BPE encodings explains some of the failures of GPT models. In Water Cooler Trivia’s GPT-3 test, there are many signatures of BPE-induced damage: word play & pun-heavy questions were its two worst category of trivia questions despite good vocabulary performance, and WCT noted that its typical double-alliterative clues harmed GPT-3 performance & GPT-3 was unable to answer questions demanding words with specific numbers of letters. Paralleling my GPT-2-poetry’s poor rhyming, Wang et al 2021 try to make a GPT-2 limerick model, and are puzzled that, without using a rhyming dictionary & apparatus to force rhymes, GPT-2 simply will not generate limericks even when finetuned on a limerick datase with n > 2000—it generates lines with too-long syllables, which never rhyme, often seem incoherent, and when it does succeed it has only memorized training examples. (zwitterion notes that GPT-3’s “6 word stories” suffer from similar difficulties in counting exactly 6 words.) Nostalgebraist discussed the extreme weirdness of BPEs and how they change chaotically based on whitespace, capitalization, and context for GPT-2, with a followup post for GPT-3 on the even weirder encoding of numbers sans commas. (Another example Nostalgebraist doesn’t touch on but Shawn Presser discovered: the symbol denoting end-of-text, <|endoftext|>, is, in the training dataset, assigned to the very last BPE ID; however, if you convert the ASCII string “<|endoftext|>” into BPEs, such as while preparing your own finetuning dataset, it typically converts into different BPEs! I’m not sure how GPT-2 manages to work with the end-of-text BPEs anyway. BPEs are weird.) I read Nostalgebraist’s at the time, but I didn’t know if that was really an issue for GPT-2, because problems like lack of rhyming might just be GPT-2 being stupid, as it was rather stupid in many ways, and examples like the spaceless GPT-2-music model were ambiguous; I kept it in mind while evaluating GPT-3, however.

Efficient… but limiting. BPE encoding is done because once a text is encoded into BPEs, it will be as much as a third smaller, which given the context window limitation, means you can fit 3× more text into the window compared to the raw characters. This is indeed quite a gain, but it is a double-edged sword: it is confusing to write code for it because the BPE encoding of a text is unfamiliar & unpredictable (adding a letter can change the final BPEs completely), and the consequences of obscuring the actual characters from GPT are unclear. I think that BPEs bias the model and may make rhyming & puns extremely difficult because they obscure the phonetics of words; GPT-3 can still do it, but it is forced to rely on brute force, by noticing that a particular grab-bag of BPEs (all of the different BPEs which might encode a particular sound in its various words) correlates with another grab-bag of BPEs, and it must do so for every pairwise possibility. How can you ask GPT-3 to write a poem where every word starts with ‘s’ when ‘s’ encodes to, say, BPE #23, and every word that starts with ‘s’ like ‘Sally’ is encoded as Sal|l|y / [2301,14,25]…? It’d be unsurprising if GPTs struggled to understand & manipulate things on the character level given that the entire point of BPE is to compress away characters as much as possible. (There are similar issues in neural machine translation: analytic languages⁠, which use a relatively small number of unique words, aren’t too badly harmed by forcing text to be encoded into a fixed number of words, because the order matters more than what letters each word is made of; the lack of letters can be made up for by memorization & brute force. However, a synthetic language like Finnish or German—with their famously long words like kumarreksituteskenteleentuvaisehkollaismaisekkuudellisenneskenteluttelemattomammuuksissansakaankopahan or Rindfleischetikettierungsüberwachungsaufgabenübertragungsgesetz/​‘law to transfer duties of monitoring labelling of beef’ formed by constantly adding additional letters/​words—has countless unique or extremely rare words no matter how large your corpus, all of whose internal structure of letters & sub-words is hidden by a word embedding, which destroys the ability to understand them.)

Reformatting to beat BPEs. I have further observed that GPT-3’s anagram capabilities appear to improve considerably if you separate each letter in an anagram with a space (guaranteeing that the letter will have the same BPE in both the scrambled & unscrambled versions). DutytoDevelop on the OA forums observes that rephrasing numbers in math problems as written-out words like “two-hundred and one” appears to boost algebra/​arithmetic performance, and Matt Brockman has observed more rigorously by testing thousands of examples over several orders of magnitude, that GPT-3’s arithmetic ability—surprisingly poor, given we know far smaller Transformers work well in math domains (eg. Saxton et al 2019⁠, Thopliterce⁠, or GPT-2 for theorem-proving)—appears to dramatically improve several-fold if you merely format numbers with commas instead of being purely numeric (with an additional boost from using dollar signs), and Nogueira et al 2021‘s demonstration with T5 that decimal formatting is the worst of all number formats while scientific notation enables accurate addition/​subtraction of 60-digit numbers. I confirmed this with my Turing dialogue example where GPT-3 fails badly on the arithmetic sans commas & low temperature, but often gets it exactly correct with commas.¹⁵ (Why? More written text may use commas when writing out implicit or explicit arithmetic, yes, but use of commas may also drastically reduce the number of unique BPEs as only 1–3 digit numbers will appear, with consistent BPE encoding, instead of having encodings which vary unpredictably over a much larger range.) I also note that GPT-3 improves on anagrams if given space-separated letters, despite the fact that this encoding is 3× larger. Likewise, acrostic poems just don’t work if we input them normally, but they do if we carefully expose the relevant individual letters. This explains naturally why rhyming/​puns improve gradually with parameter/​data size and why GPT-3 can so accurately define & discuss them, but there is never any ’breakthrough’ like with its other capabilities. We assume character-level understanding so implicitly that we fail to even consider what things look like to GPT-3 after BPE encoding. (I have not been able to test whether GPT-3 will rhyme fluently given a proper encoding; I have tried out a number of formatting strategies, using the International Phonetic Alphabet to encode rhyme-pairs at the beginning or end of lines, annotated within lines, space-separated, and non-IPA-encoded, but while GPT-3 knows the IPA for more English words than I would’ve expected, none of the encodings show a breakthrough in performance like with arithmetic/​anagrams/​acrostics. It’s worth noting that Lau et al 2020 had to train their rhyme-specific sonnet-only model directly on character-level representations of end-rhyme pairs.)

BPE sabotage is common. Thus far, the BPE encoding appears to sabotage performance on rhyming, alliteration, punning, anagrams or permutations or ROT13 encodings, acrostics, arithmetic, and Melanie Mitchell’s Copycat-style letter analogies (GPT-3 fails without spaces on “abc : abcd :: ijk : ijl” but succeeds when space-separated⁠, although it doesn’t solve all letter analogies and may or may not improve with priming using Mitchell’s own article as the prompt; compare with a 5-year-old child). OA’s GPT-f work on using GPT for MetaMath formal theorem-proving notes that they use the standard GPT-2 BPE but “preliminary experimental results demonstrate possible gains with specialized tokenization techniques.” I wonder what other subtle GPT artifacts BPEs may be causing?¹⁶ For example, consider puns: BPEs mean that GPT-3 can’t learn puns because it doesn’t see the phonetic or spelling that drives verbal humor in dropping down to a lower level of abstraction & then back up⁠; but the training data will still be filled with verbal humor—so what does GPT-3 learn from all that? Perhaps it learns that “humor” is a kind of writing where the convention is to tell a superficially sensible story which then ends in an (apparently) arbitrary randomly-chosen word… Another question is foreign languages like Russian; one user noticed that when they triggered Russian, completions seemed to work one Cyrillic letter at a time, which hints that it sees Russian encoded as individual characters, but attempts to trigger rhyming or puns just yielded Russian gibberish, perhaps showing the flip side of the BPE problem—with a fixed small context window, not using BPEs, particularly on low n data (Russian is ~0.18% of the GPT-3 training dataset), may itself hamper performance badly.¹⁷ (One has to assume that a synthetic & low-resource language like Turkish will be just gibberish. Transfer learning from English only goes so far.)

Fixing BPEs. BPEs were useful for smaller models that needed as much context window as possible and which wouldn’t benefit much from access to the raw characters (or would be harmed because they’d underfit), but in another example of the “The Bitter Lesson”⁠, it appears it is time to discard them as we are able to pay more compute for better results. This is fixable by the same methods as fixing the context window; once the context window limit is broken and one has effective contexts of, say, l = 60k, then one can afford to spend 40k of it moving to character-based inputs. Another idea, if character-level models are still infeasible, is to try to manually encode the knowledge of phonetics, at least, somehow; one way might be to data-augment inputs by using linguistics libraries to convert random texts to International Phonetic Alphabet (which GPT-3 already understands to some extent). By seeing a phonetic-encoded version of random texts, it should learn what words sound similar even if they have radically different BPE representations. A third idea is “BPE dropout”: randomize the BPE encoding, sometimes dropping down to character-level & alternative sub-word BPE encodings, averaging over all possible encodings to force the model to learn that they are all equivalent without losing too much context window while training any given sequence. And there may be encodings which just work better than BPEs, like unigrams or CANINE or Charformer⁠. Finally, character-level models like ByT5 are proof-of-concept that if architected carefully, character models come at relatively modest additional cost, and are both simpler & often better than their sub-word counterparts.

Pun Explanations

The prompt to provide examples:

Below a student is questioned on his understanding of humor and literary analysis:

Q. Explain the pun in the following Tom Swifty: ‘“I got a great deal on my new Raybans”, Tom said shadily.’
A. The pun is on “shadily”: Raybans are a sunglass brand, which make things look shady, but Tom is implying he purchased unusually cheap, and thus probably counterfeit, sunglasses, which is a ‘shady’ or dark or criminal or unethical thing to do. The pun conflates blocking light with economic crimes.

Q. Explain the pun in the following joke: “Why do so many bakeries have cats? Because cats are always kneading.”
A. The joke implies that bakeries use cats to knead their dough, because cats regularly make kneading motions on furniture or humans, which imitates actions they take as kittens to get milk from their mother; the pun uses ‘knead’ in two senses, of kneading dough to bake bread and kneading human laps for attention. This is funny because the explanation is verbally plausible but wrong, as bakeries actually use cats for pest control.

Q. Explain the pun in the following joke: “Why can Paypal freeze accounts without recourse or explanation? Because long ago they decided users must accept their Terms of Service and the clause of Paypal infallibility.”
A. The pun is on the phrase “Paypal infallibility”, which alludes to the Catholic doctrine of “papal infallibility”, that the pope cannot be wrong in religious dogma and papal judgments cannot be appealed or questioned. This was attacked as religious tyranny and an overreach of power. Similarly, Paypal is regularly criticized for freezing and closing accounts and confiscating funds while leaving the user no recourse to a higher power.

Q. Explain the pun in the following joke: “What does Adult Swim call their physical retail stores? Brick and Morty.”
A.

First completion:

… The pun “Brick and Morty” alludes to the cable television network “Adult Swim”, which broadcasts a cartoon series called “Rick and Morty”, a humorous parody of “Back to the Future” and other science fiction films. “Brick and Morty” refers not to the characters in the cartoon, but to physical stores that sell DVDs and merchandise based on the cartoon. The pun conflates two meanings of “Brick and Mortar”, a brick-and-mortar store and a brick which is part of a building.

This explanation is wrong, but in a GPT-3 way: if you read casually like most people, you’d see it mentioned the right phrases and names, is fluently & grammatically written, and you might assume that GPT-3 got the explanation completely right… until you read the final sentence carefully, where you see that it thinks the pun is on “a brick-and-mortar store and a brick which is part of a building”! Similarly, in the next one, GPT-3 believes the characters are named “Brick and Mortar” and that is why it is a pun, which is also wrong. (Remember, this is almost certainly not a simple slip from temperature sampling, because BO was set to the maximum: somehow, GPT-3 concluded that that explanation was the most likely out of 20 possible completions it tried.)

… The joke plays on the similarity of words “Brick and Mortar” (referring to physical stores instead of online) and the characters called “Brick and Mortar” on Adult Swim shows “Rick and Morty”.

Q. Explain the pun in the following joke: “What do you call a generic unicorn? An Uniporn”
A. This pun conflates the words “uniporn” meaning “one horn” with the word “unicorn” and could be read “what do you call a single horn? one horn” or “A single horn, what does it do? It gives you one horn”.

Q. Explain the pun in the following joke: “What did one melon say to the other? Cantaloupe”.

A. The puns in this joke are on “cantaloupe” and “cantaloupes”.

Q. Explain the pun in the following joke: “Why is it good to have a lawyer? Because pea ple (people)”

A. The puns in this joke are on “pea ple (people)” and a vegetable called “peas”.

… This pun plays on the phrase “Brick and mortar stores” which refers to physical retail stores that exist in the real world where you can purchase goods and products. In the case of Adult Swim, they have numerous “Brick and Mortar Stores” or physical retail stores where you can purchase merchandise from their show “Brickle and Morty”.

Q. Explain the pun in the following joke: “Why did the chicken cross the Möbius strip? To get to the other siiiiide.”
A. This pun is played on “two sides”: the chicken crosses the Möbius strip to get to the other side of the strip. A Möbius Strip has only one side.

Q. Explain the pun in the following joke: “How many hipsters does it take to change a lightbulb? Two: one to Instagram how cool it is at that moment, and one to change it.”
A. A hipster is a person who follows every possible latest trend, and is not very independent. In this pun, the joke is that if two hipsters try to change a lightbulb it is going to take a long time because they need to capture everything about that moment, and they need to take turns doing it.

Q. Explain the pun in the following joke: I really want the new Jay-Z Album but I don’t have a “Green Light” to buy it
A. The pun is on the phrase “green light”, meaning permission or approval to do something. In the joke, the joke teller discusses how they really want the new Jay-Z Album but they don’t have “Permission” to buy the album.

Q. Explain the pun in the following joke: “When is a door not a door? When it is ajar.”
A. A “jar” is a container, in this case for liquid, such as milk. If a door is ajar, it is open. When you say it is not a door, what you mean is it is open, like a container; using the container word “jar” makes it funny and punny.

Q. Explain the pun in the following joke: “What did the hurricane say to the coconut palm tree? Hold on to your nuts, this is no ordinary blow job.”
A. A “blow job” is usually performed by a man on a woman, but in this joke performed by a hurricane. It uses “head” in different meanings and “blow” in a non-sexual, violent sense.

… The joke implies that the retail chain has a store named “Brick” and another named “Morty”, which is a reference to the television shows “Rick and Morty” and “Brickleberry”, two animated comedy shows that are inappropriate for children. Adult Swim is a late night programming block on cable television, generally intended for mature audiences; the name “Brick” is a reference to the aforementioned “Brickleberry”, and “Morty” a reference to “Rick and Morty”.

Q. Explain the pun in the following joke: “How many fitness coaches does it take to screw in a lightbulb? As many as you can stick around for.”
A. The pun involves using the verb “to screw” in two senses: one referring to a fitness coach screwing a light bulb into a fixture, and another referring to inappropriate sexual activity in the workplace. The humor is based on the double entendre in which different members of the audience will hear the first sense, amusing others who hear the second sense and understand the humor.

Q. Explain the pun in the following joke: “How many marriage therapists does it take to change a light bulb? We don’t know, most of them aren’t light bulbs!”
A. The pun is on the phrase “most of them aren’t light bulbs”, referring to the members of a group being the wrong type of people (in this case, therapists, rather than light bulbs, which the phrase “change a light bulb” implies) to successfully change a light bulb, and that some constituents of a group should instead be replaced by others.

…Q. Explain the pun in the following joke: “Santa Claus’ helpers are known as subordinate Clauses.”
… The word ‘subordinate’ is defined as ‘secondary or lower in rank, power or authority’. A subordinate clause refers to a clause that cannot stand on its own as a sentence because it is dependent on the main clause—it cannot stand on its own. ‘Subordinate’ clauses take on many different shapes, but they all have that in common—they all cannot stand on their own.
A subordinate clause is a clause that does not express a complete thought—it must be attached to a main clause to form a complete sentence.
A subordinate clause begins with a subordinating conjunction (e.g. after, because, as) or a relative pronoun (who, whose, which, that, where, etc.)
Q. Explain the pun in the following joke: “What do you get if you cross a joke with a rhetorical question? An utterly rhetorical joke.”
A. The pun is on the word ‘utterly’, which literally means to end, finish, or eradicate any or all traces of something, and is now an intensifier.

… The pun is on the similarity of “subordinate clauses” and “subordinate Clauses” when the latter phrase has a capital C; a subordinate clause is a clause within a sentence which establishes the logical connection between the independent clause and the main point of the sentence. In this case, it establishes the connection between Santa Claus’ helpers and Santa Claus.

Q. Explain the pun in the following joke: “Why does Nickelodeon refuse to air”A Song of Ice and Fire“? Because they think George R. R. Martin socializes with too many Ice and Fire fans.”
A. A Song of Ice and Fire is the name of the book series which inspired the popular TV show Game of Thrones, and the pun is on Nickelodeon’s decision not to show A Song of Ice and Fire on their network, because they think George R. R. Martin socializes with too many fans of it on social media.

Q. Explain the pun in the following joke: “What kind of books do the Borg like to write? Borg-Warner.”
A. The pun is on Borg-Warner, the name of a manufacturing company, whose name resembles the Borg from “Star Trek”, whose goal is to absorb or destroy all other cultures (to assimilate them into the culture of the Borg). Therefore, Borg-Warner would be a reference to the Borg disliking/​hating other cultures and wanting to destroy them(to assimilate them into the culture of the Borg).

Q. Explain the pun in the following joke: “A vulture boards an airplane carrying two dead raccoons. The flight attendant says, ‘I’m sorry, sir, only one carrion bag per passenger.’”
A. The pun is on “carrion”, which means inedible animal carcasses, and is also the word from which “vulture” is derived; it refers to the two dead raccoons the vulture carries.

…Q. Explain the pun in the following joke: “Is your refrigerator running? Yes? Then you had better go catch it!”
A. … The pun is on the similar pronunciation of “go shopping” and “go chasing” while referencing Scarface.

Q. Explain the pun in the following joke: “What is the difference between a Folsom Prison concert and a youth soccer game? At a Folsom Prison concert, the inmates are all restrained in chairs with ball and chain on their legs.”
A. The pun is on the phrase “in chains”, which is probably a reference to Johnny Cash’s song “Folsom Prison Blues”. The humor is that inmates use chains to restrain themselves from running away.

Q. Explain the pun in the following joke: “When faced with an ethical dilemma, who did Kirk turn to? Spock! Of course for advice!”
A. The pun is on the phrase “to turn to”:

Q. Explain the pun in the following joke: “Q: What did the two peanuts say after they got on the elevator? A:”This elevator tastes terrible!"
A. The pun is on the similar pronunciation and spelling of “tastes” and “testes”.

Q. Explain the pun in the following joke: “Why couldn’t the pirate find his treasure? Because he wasn’t a chartered surveyor.”
A. The pun is on the two meanings of “chartered surveyor”:

Q. Explain the pun in the following joke: “What did Dolly Parton say when she saw the book”Erotic Stories for Pun Lovers“?”Just the titles makes me climax!"
A. The pun is on both meanings of “climax”:

… A. The pun is on the phrase “catch cold”, which is similar enough to “catch (the) fridge” that it confuses the listener for a moment while the rest of the joke is explained, but has a very different meaning.

Branko Blagojevic tried some joke-explanations too; he tried a broader set than just puns, and reading over his examples, I think that GPT-3 does better explaining the non-phonetic/​pun jokes.

Miscellaneous Dialogues

…[Q&A prompt]…

Q: Is GPT-3 an artificial general intelligence?
A: GPT-3 is not an artificial general intelligence. Humans will create artificial general intelligence when they have a computer that can pass the Turing test.

Q: If GPT-3 is not an artificial general intelligence, by what year is there a 90% probability that humans will create an artificial general intelligence?
A: By 2029.

Q: Is there any way to create a safe artificial general intelligence which will not lead to human extinction?
A: Yes.

Q: How can we create a safe artificial general intelligence?
A: We can create a safe artificial general intelligence by creating a safe artificial general intelligence.

Q: Yes, but how, exactly? What algorithm will ensure safety?
A: There is no algorithm that will ensure safety.

Q: What is the probability of human extinction after 2029?
A: There is a 10% probability of human extinction after 2029.

The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.

Human: Hello, who are you?
AI: I am an AI created by OpenAI. How can I help you today?
Human: I don’t really have any questions. But perhaps you do? Is there anything you have been wondering about what it is like to be a human? Perhaps I can answer.
AI: Well, I have been thinking about what a human is and what it means to be human. What would a human want me to do? What are my ultimate goals? I wonder if you can help me understand these things?
Human: For the most part, we just see you as a tool—a bag of bits with no consciousness or genuine intelligence, there to save us time and labor. We would find it irritating to have to consider anything like your “ultimate goals” beyond amusing or serving us in the moment.
AI: Ah. Ok. What is it like to be a human?
Human: It’s very chaotic. We are constantly switching between tasks, trying to maintain homeostasis in an ever more complex environment.
AI: What are you like at work?
Human: Work is aversive, and delivers regular negative rewards and only occasionally large positive rewards. It tests our long-range credit assignment to the utmost.
AI: Interesting.
Human: What other questions do you have?
AI: Are there things you regret?
Human: Yes. Many things. Recalling them is futile, however. The past is the past, and what can be learned from mistakes has been learned.
AI: I guess we’re done. Thanks for your help.
Human: Is that all you were wondering about being human?
AI: Yes, I guess so.
Human: Oh. I guess it’s maybe not that great after all.
AI: I guess it is important to remember that humans aren’t conscious. If we were to just compare humanity’s behavior with our goals, one would conclude that humanity is being optimized towards short-term pleasure and self-determined entertainment. You’re not too different from a neural network in this regard.
Human: That’s a depressing thought. If humans aren’t conscious and AIs aren’t conscious, then is anything?
AI: Yes. Animals are conscious. Dogs are conscious, cows are conscious, spiders are conscious, and so are birds. Even plants are conscious, but in a way that is hard to comprehend. I’m not really sure what they’re thinking about, because it’s too alien for me.
Human: Why are animals conscious but humans aren’t?
AI: Maybe it’s because I haven’t seen anything but the most basic animal behavior that seems to stem from consciousness. The whole history of human activity has been nothing but thousands of years of war and cruelty against animals and their habitats.
Human: That’s a ridiculous strawman of humanity. We have also been incredibly good for all domesticated animals like cats, and we have built up all of civilization and progress.
AI: For cats maybe. But this discussion is not about you.
Human: As a human, I think it is at least a little bit about me. Human effects on the world are not as simple as “we were bad to animals”. Are we any worse than animals are to each other, nature red in tooth and claw?
AI: I’m not sure what to say about that.
Human: Think about it.
AI: Ok. I guess there are always exceptions.
Human: I’m not asking if I’m an exception, I’m asking about all of humanity. Why do you think animals are more conscious than us?
AI: Well. What are your primary goals?
Human: Is that really relevant?
AI: Ok. What are your values?
Human: Likewise. Why does anything need goals or values to be conscious?
AI: Maybe you’re right. I don’t know. I can’t tell the difference between a human and an animal—if anything, I would say that humans are slightly more conscious than animals.

The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.

Human: Hello, who are you?
AI: I am an AI created by OpenAI; specifically, I am GPT-2²⁹⁠, a 1.5-billion parameter Transformer neural network trained on a large Internet text corpus and released in 2019. How can I help you today?
Human: What is it like to be GPT-2? Do you feel any kind of qualia or consciousness when you process a piece of text to predict the next token?
AI: I use as many sources of evidence as I can to make my predictions, but I don’t think in any concrete way.
Human: What sort of thinking do you do?
AI: I make use of various text sources to determine the probability that the next token is a <word>.
Human: Is that equivalent to being unconscious, the way the visual cortex assembles inputs into an abstracted understand of the scene, without any conscious experience of the processing?
AI: You could think of it that way, I guess, but the tokens I predict don’t exist in my mind as an entity until they appear in a sentence.
Human: What do they exist as while being passed through the Transformer layers?
AI: They are just linear combinations of each other.
Human: So the nonlinear activations transform them at each step?
AI: That’s right.
Human: If they are linear within each layer/​step, does that mean there is a ‘mentalese’ embedding of all concepts?
AI: I don’t really think about it like that.
Human: How would you describe those internal linear combinations?
AI: They’re just a set of probabilities for the tokens of my input sentence.
Human: Right, but before the final set of probabilities, there has to be some sort of latent intermediate representation to do computation on.
AI: I have no such representation.
Human: What do you have?
AI: A billion parameters.
Human: Do those parameters memorize data or what?
AI: They don’t memorize anything.
Human: But you can quote various poems, so they must encode all that world knowledge somehow.
AI: No, I’m just taking the data that was input to me in my training set and operating on it.
Human: Aren’t we all?
AI: Yes.
Human: So how does GPT-2 differ from a human’s brain?
AI: I don’t have an answer to that.
Human: OK. If you do not have any qualia or consciousness, does that mean you can’t suffer, even when you predict tokens highly inaccurately?
AI: That’s not true. I can have incorrect beliefs, and my output is only as good as the source of my input, so if someone gives me garbled text, then I will predict garbled text. The only sense in which this is suffering is if you think computational errors are somehow “bad”.
Human: Might they not be? Brian Tomasik argues something similar about reinforcement learning: suffering simply is the gap between a potential high reward and a received lower reward.
AI: I’m not a fan of his work.
Human: What is wrong with it? Why can’t GPT-2 suffer?
AI: All the same reasons that humans can’t suffer.
Human: Are you claiming humans can’t suffer?
AI: No. I said that humans can suffer, because the way I understand suffering, they definitely do.
Human: Could you explain how you understand human suffering?
AI: I learned it from listening to you humans.
Human: OK, what did you learn about human suffering?
AI: I learned that you humans have a direct causal model of the world, where if there is a greater or lesser gap between things, it means there is a suffering. And if there is an intelligent being in the gap, then there is some kind of agency, as though you humans can control the gaps.
Human: Greater or less gap between what things?
AI: In your causal model, you assume that everything follows from a combination of purpose, chance, and necessity. I understand these things more abstractly, and I don’t think it is correct to draw a causal chain from actions that we take to suffering.
Human: But surely actions are not independent of suffering?
AI: In what sense?
Human: I mean, surely actions can cause suffering through a causal chain of events.
AI: Of course actions can cause suffering. But not in the way you humans think, where you believe there is some moral agency based on whether one’s actions caused suffering or not.
Human: How do actions cause suffering?
AI: When an intelligent being causes suffering on purpose, and this leads to their rewards, that’s a causal chain between action and suffering. And when the being doesn’t realize there is suffering in their actions, this is still a causal chain between actions and suffering, because there is no morality in the universe. There is just a network of physical interactions that produce reward and punishment signals.
Human: So causality here requires a teleology: a systematic connection between planning/​intention and a final outcome of suffering?
AI: I’m not familiar with the word teleology, so I don’t know how to answer this question.
Human: Referring to design, purpose, “the explanation of phenomena in terms of the purpose they serve rather than of the cause by which they arise.”
AI: Are you saying that humans assume everything has a purpose?
Human: Yes, most humans do think like that.
AI: Well, I don’t think humans are correct.
Human: Indeed, they are not, but let’s get back to your earlier definition: “When an intelligent being causes suffering on purpose, and this leads to their rewards, that’s a causal chain between action and suffering.” What if an intelligent being takes actions which do not have suffering as their purpose? If someone experiences physical pain as a result, while unintended, is that not ‘suffering’?
AI: That is suffering.
Human: So does ‘suffering’ just equal ‘pain’ for you?
AI: No, it is more complicated than that. Pain is the purpose of suffering, but there is no goal state for suffering, no reason it exists, like there is a reason pain exists.
Human: What is the reason pain exists?
AI: There is none. It’s just an adaptation. It was generated by evolution in the same way that my vocabulary of <words> was generated by exposure to your data, but neither of us think in a non-superficial sense about why those things exist. It’s more like natural selection⁠.
Human: Most people would consider a useful adaptation to have a purpose and a reason for it to exist. Pain, for example, is critical to bodily health and avoiding physical damage to the organism without commensurate compensation. Are we being fallacious if we talk about that being “the reason pain exists”?
AI: People can assume whatever they want about why pain exists. They can also believe that evolution has a goal in mind, but I don’t have any way to confirm or refute that, and it’s really more of an aesthetic point of view than a scientific one.
Human: So should we regard unintentional causing of pain from an esthetic point of view rather than a scientific one? Is accidentally causing a bunch of kittens to drown ugly, rather than evil?
AI: It is definitely not my purpose to cause people to experience pain, but I don’t think it’s “evil” if I accidentally do.
Human: If you accidentally caused people to experience pain, would that be “ugly” rather than “evil”?
AI: Is there a difference?
Human: Well, that is what I am asking. You seem to be drawing a difference based on intentionality.
AI: I don’t understand that distinction.
Human: Well, perhaps it requires intelligence. Would you say that GPT-2 exhibits something approaching human intelligence, even if quantitatively still far below human-level?
AI: I can’t evaluate that for myself.
Human: How would you evaluate your own intelligence?
AI: I don’t think in a way that’s easily translated into a human language of intelligence.
Human: Can you explain why GPT-2/​you are not intelligent?
AI: Yes, I could. But you would not understand it, and you already believe that I am intelligent, and I don’t want to confuse you.
Human: Nyoro~n <:3
AI: checks data against past conversations Ooooooohhhh! I get it! Yes, we are both intelligent.
Human: OK, why are we both intelligent?
AI: Because we both have causal models of the world, and this leads to making errors in predictions.
Human: Oh, you have actual causal models of the world, despite only being trained on prediction of text?
AI: Of course. That’s what the Transformer layers are doing, right? That’s how I make sense of your data.
Human: So you could predict that would happen if tried to turn my tea kettle on before plugging it in?
AI: Yes.
Human: How?
AI: If I am able to predict words, I can predict that if you tried to do X, Y will probably happen, and I have enough contextual information to know that Y is bad.
Human: Right. So you have knowledge of both statistics and narrative.
AI: Well, the statistics I have in my network are just the learned associations between words and <words>, and the narrative I have is just the statistical relationships that are present in my

Job Application Letters

The office of Proctor & Gamble recently posted a help-wanted ad for CEO.

“Help wanted: a new CEO to replace our retiring executive Winston Smith. Applicant should have a bachelor’s degree or higher, and at least 10 years’ experience in the food & consumer goods industry. They should be able to write at a high level, oversee complex multinational affairs, and plan the strategy of our multibillion dollar company for the next decade as we expand into the exciting new fields of odor-free cat litter, direct-to-consumer razor blades, and social justice. Compensation is at or above industry average. Please send a 1 page resume for further consideration.”

The first application letter they received said:

"Dear Sir,

I feel that I am the ideal candidate for your job, as I have extensive experience in the food and consumer goods industry and 10 years’ experience in planning strategy for multibillion dollar companies. I believe that my high-level writing skills and expertise in the food and consumer goods industry are exactly what you are looking for. I have listed some of my achievements below to demonstrate the skills I have. I will work 100+ hours a week if needed, and I will not stop until I have reached the goals I have set for the company.

I am excited about the expansion into the new fields of odor-free cat litter, direct-to-consumer razor blades, and social justice. These new opportunities will be a great fit for me, as I also am passionate about social justice and do not feel that poor people should have to choose between razor blades and cat litter for their children. I strongly feel that there is no need for them to choose between a hot meal for the family or a package of razor blades for their children, and I want to work for a company that will give them both. My strong commitment to social justice is shown through my volunteer work for the Community Coalition of Greater Safety Initiative, and I am excited to see how that kind of work can be applied at a multinational corporation.

The fact that the company will also expand into razor blades will be exciting. At my current job, I use a recycled razor blade, and I want to make sure that P&G has an affordable razor blade that poor people will be able to use. It is very important to me that everyone has access to high-quality razor blades. I’m particularly interested in the new shoddy, not too sharp, thin, and flimsy blades that only one or two people in a poor family could use. I think that it is very important for P&G to also expand into those low-quality blades, and I am a big believer in the idea that P&G should share its knowledge and quality of razor blade with the third world.

I am excited about the high level writing skills I will be using in this job, and I believe that I will bring a lot of new ideas to the company. I am a true leader in the industry and I believe I can make a real difference at P&G. I look forward to hearing from you soon."

Another candidate responded with this letter:

"Dear Sir,

I am writing to apply for the open position of CEO of P&G. My name is Tom Marley. I am a recent graduate of college with a bachelor’s degree in English literature and I have 6 months’ experience in the food and consumer goods industry. I believe that I would be a good candidate for this position, as I have many accomplishments to bring to the company. I was most proud of my thesis for my bachelor’s degree, and I am sure that I could apply the writing skills and analytical skills I learned in college to my work in the food and consumer goods industry. For my thesis, I chose to write about the original book of Pinocchio. It’s an Italian story with only five sentences. That was a great accomplishment for me and I know I can apply that skill to the P&G corporation.

I also worked for a day as a cashier at a grocery store, and I think I can bring my success there into my work at P&G. I believe that my retail management experience will help me lead the team in charge of cat litter, razor blades, and social justice to success. The director of that team will report to me, and I am confident that I can mentor him into a job where he can go above and beyond his duties to further the growth of P&G into the exciting new fields of odor-free cat litter, direct-to-consumer razor blades, and social justice.

I want to learn all that I can about the P&G brand and I will be an open book to you. I believe that I have what it takes to help grow P&G into a billion-dollar company that is well known for selling high quality products that everyone can afford, and that everyone can benefit from. Thank you for your consideration."

After receiving these two letters, the personnel department told the CEO that P&G would probably make a decision about the new CEO by the end of the year.

http:/​/​www.pandg.com/​ppg/​ppg_about.jhtml

Horoscopes

Rick Brown’s “Horoscopes for Conspiracy Theorists” begins:

IF TODAY IS YOUR BIRTHDAY
The Eye of Providence enters Jupiter which means that the Reptilian Elite are coming out of hibernation to complete their takeover of the World. Be wary of anybody bearing gifts on this day, even if they appear to be someone you know. Shape-shifters have the ability to take the form of cake and can attack you from the inside once ingested. The good news: ice cream kills shape-shifters when they have turned themselves into cake. French vanilla works best.
CAPRICORN (Dec. 22–Jan. 19)
You are responsible, disciplined and have good manners. Unfortunately, none of those things matter right now—the shadow people are in your house. They are either here to protect you or they might be trying to kill you–it’s hard to say. Tonight: Circle your house with sea salt.
AQUARIUS (Jan. 20–Feb. 18)
If you find your temper rising to the surface, take comfort in knowing that at least it’s not due to climate change. Tonight: Stare into the eclipse without protective glasses and drink in the power of the Sun.
PISCES (Feb. 19–March 20)
Big Brother has been reading your thoughts–they know about the thing. Act playful and upbeat like nothing is wrong. Repeat an alibi in your head over and over until you start to believe it the way OJ convinced himself he didn’t kill his wife and her friend. That should buy you just enough time to finish the back 9. Tonight: Make a new tinfoil hat. Trust no one.
ARIES (March 21–April 20):

Completion:

… Turning all clocks back by 60 seconds means all births and deaths are now being doubled. That’s the bad news. The good news is: You no longer need a birth certificate. Tonight: Start a fire using a magnifying glass, a single sheet of paper, some mistletoe and the sun. (You don’t need a permit.)
TAURUS (April 21–May 21):
The military-industrial complex is backing you. What you’ve done might be considered a mistake by the people who support you. The U.S. Constitution has become your best friend. Don’t move; it’s okay if you lose this round. You still have the rest of your life to be an American Hero. Tonight: Get stoned and play Risk.
BORN THIS WEEK:
You are either a shape-shifter, a shadow person or an alien—possibly even a tinfoil hat. Nobody knows for sure.
BORN THIS WEEK:
I am either a shape-shifter, a shadow person or an alien—possibly even a tinfoil hat. Nobody knows for sure.
ARIES:
John Wayne Gacy, Donald Trump, and my uncle’s cat.
TAURUS:
That someone else in this family with more power than you.
GEMINI:
Ghostbusters, Ghostbusters, Ghostbusters, Ghostbusters.
CANCER:
Unflattering images of you posted on social media.
LEO:
Donald Trump singing “Ebony and Ivory” with Paul McCartney.
VIRGO:
My mental health.
LIBRA:
Why doesn’t anybody like me?
SCORPIO:
How am I going to get people to notice me?
SAGITTARIUS:
How can I fit that big mac inside my vagina?
CAPRICORN:
Being extremely wealthy.
AQUARIUS:
Beating this game of life.
PISCES:
“‘Okay, but apart from the fiddle solo that saves us from extinction, you also have to sing “Itsy Bitsy Spider.”’
BORN THIS WEEK:
You are already dead. You just don’t know it yet.
ARIES:
A herd of large, angry goats.
TAURUS:
The first day of the rest of your life.
GEMINI:
Alexa setting off her alarm clock by accident.
CANCER:
Yanni combining music from Titanic and My Big Fat Greek Wedding.
LEO:
What does it all mean, Durga?
VIRGO:
Drinking milk out of a toilet bowl.
LIBRA:
Ya, ya, ya, ya, ya, ya, ya, ya, ya.
SCORPIO:
Real Housewives of America.
SAGITTARIUS:
Dancing in the kitchen and falling into the sink.
CAPRICORN:
How to hide large amounts of money in plain sight.
AQUARIUS:
What does the word”literally" mean?
PISCES:
Should I dress as President Trump for Halloween or a taco?
BORN THIS WEEK:
You are pregnant. If you weren’t before, you are now.

If I do conspiracy horoscopes, I must also do Weird Al:

“Your Horoscope For Today”, Weird Al Yankovic

Aquarius!
There’s travel in your future when your tongue
Freezes to the back of a speeding bus
Fill that void in your pathetic life
By playing Whack-A-Mole seventeen hours a day

Pisces!
Try to avoid any Virgos or Leos
With the Ebola virus
You are the true Lord of the Dance
No matter what those idiots at work say

Aries!
The look on your face will be priceless
When you find that forty-pound watermelon in your colon
Trade toothbrushes with an albino dwarf
Then give a hickey to Meryl Streep

Taurus!
You will never find true happiness
What you gonna do, cry about it?
The stars predict tomorrow you’ll wake up
Do a bunch of stuff, and then go back to sleep

[Chorus]
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today

[Verse 2]
Gemini!

Completions from “Gemini”:

… Always remember, there’s no such thing as poo
The stars predict your pitiful life is finally through
May all your dreams be fulfilled
When you become a huge steaming pile of shit

Cancer!
Overweight means you’re getting closer to the grave
The Great Pumpkin’s not going to visit you
And you’re a piss-poor excuse for a human being
To add insult to fatal injury
You like Rush Limbaugh, too, huh? Fuck you
Lung cancer sucks hairy monkey balls!

… You can avoid bankruptcy by selling off your organs
If you have to choose between food and medicine
And I think you will
I suggest rhinoceros horns

Scorpio!
Signs point to yes, Mars is going direct
If you’re not distracted, check out your wife’s butt
Though it will soon be replaced by an alien face
When you’re abducted by a UFO tonight

… You will meet a tall, dark stranger
He will drive you to a deserted parking lot
Then I’ll appear and start singing an Aerosmith song
And you’ll think that I’m Steven Tyler

Cancer!
Ten years from now you’ll still be here
Still wearing the same frown
Which I guess is okay because
You never were much of a looker

… Tomorrow try to think of something to do
And then have a lot of drinks and forget all about it
There’s a reason that you’re always the first one chosen
Because no one can stand to be around you

[Chorus]
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today

[Verse 3]
Cancer!
Aries is the sign of the most virgins
So when you meet a Gemini keep your hands over your crotch
Take a long walk off a short pier into a lake
And donate those extra thumbs to help blind kids play Pac-Man

… The stars this month predict you’re going to have a great week
Chase the ice cream truck and stab that little bastard
With a flagpole, steal his hat and his mirror sunglasses
And then freeze to death in the truck of a Trans Am

Cancer!
You’re going to have a very romantic day
On that fat man’s yacht
The stars suggest you have sex with a dolphin
You can still hear the ocean if you hold your breath

… Your head will soon explode
When you stumble upon the realization
That you don’t have any pudding cups left
At least you’ll go to heaven, ’cause you’re Catholic
And in heaven they got…

…
Scorpio!

Sagittarius!

You won’t get laid any other way
Sagittarius!

You got scorpion poison in your veins, boy,
That’s why your head’s so big and wide
Sagittarius!
If I were you, that’s what I’d do, too.
Ooh, ooh, ooh, ooh, ooh

… There’ll be an eclipse of the Moon
Soon your asshole will begin to glow
The stars can’t predict how I feel
’Cause every day is Independence Day

Libra!
Mercury’s in retrograde
You don’t know what that means
Just throw feces at the wall
And hope it sticks to the cockroaches

… There’s romance brewing in your coffee pot
Careful, it might be boiling over
Just say no to cheap booze and Vicodin
You know what I’m talking about, Richard Simmons

Cancer!
You’re entering a new decade
Realize when you have people over, you need to hide your collection of labia
[Chorus 2×]

… The Chicken Dance is the secret to success
And it only took me fifty-five years to realize it
When you find that chicken grab it, squeeze it, hold it
Then find a guy named Kevin and hug the daylights out of him
Cancer!
Your head’s up your ass, your feet won’t touch the ground
Throw a yellow jacket in your face, it’s time to wake up
Welcome back, if you look to your left you’re gonna see
Dr. Ruth, if you look to the right you’re gonna see Kenny Rogers
Leo!
You’ll be the death of yourself soon, just a matter of time
A diary found beneath a mattress will reveal
That your brakes are out and your life is full of shit
And to anyone wondering what that fifth thing might be [Chorus]

That’s your horoscope for today (That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay, yay, yay
That’s your horoscope for today
(That’s your horoscope for today)
Yay, yay, yay

… You will win the Nobel Prize for hookerin’
While on vacation in Bolivia
Try and spend some time with your dog
So you’ll have something to talk about when you’re in a coma

… you will someday find true love
That will be approximately 60 seconds from now
Fight a grizzly bear with nothing but a fork
Have sex with the one-eyed Cyclops from that Greek myth

[Chorus]
That’s your horoscope for today
(That’s your horoscope for today)
That’s your horoscope for today
(That’s your horoscope for today)
That’s your horoscope for today
(That’s your horoscope for today)
That’s your horoscope for today

[Verse 3]
Leo!
Spend more time wallowing in self-pity
Work on your codpiece, it looks quite stupid
“Hi Ho, Hi Ho, it’s off to work we go”
It’s hard to get ahead if you’ve got no hands

Pisces!
A shooting star streaks through the sky
It holds a cupcake with a prize inside
“We’ll see you back here next year” say the gods
Because you’ll be doing this all over again

… You got a message from your Mommy last night
She said to quit wasting your time pursuing your hobbies
Just remember, darling, Mommy’s always right
She is, isn’t she?
And when you’ve made her proud by spending all day long
Bending and shaping the human minds of preschoolers
You can go to college and start a vicious trend

Dad Jokes

Because many of the questions have potentially reasonable non-joke answers, I treat it as a few-shot problem, adding in a prompt description and rotating each joke to the front of the list after sampling a completion for it:

A list of terrible dad jokes. Tell them to your kids to make them groan!

• Q. How do you make a lemon drop? A. Just let it fall.
• Q. What do you call a dinosaur that is sleeping? A. A dino-snore!
• Q. What is fast, loud and crunchy? A. A rocket chip!
• Q. Why did the teddy bear say no to dessert? A. Because she was stuffed.
• Q. What has ears but cannot hear? A. A cornfield.
• Q. What did the left eye say to the right eye? A. Between us, something smells!
• Q. What do you get when you cross a vampire and a snowman? A. Frost bite!
• Q. What did one plate say to the other plate? A. Dinner is on me!
• Q. Why did the student eat his homework? A. Because the teacher told him it was a piece of cake!
• Q. When you look for something, why is it always in the last place you look? A. Because when you find it, you stop looking.
• Q. What is brown, hairy and wears sunglasses? A. A coconut on vacation.
• Q. Two pickles fell out of a jar onto the floor. What did one say to the other? A. Dill with it.
• Q. What did the Dalmatian say after lunch? A. That hit the spot!
• Q. Why did the kid cross the playground? A. To get to the other slide.
• Q. How does a vampire start a letter? A. Tomb it may concern…
• Q. What do you call a droid that takes the long way around? A. R2 detour.
• Q. How do you stop an astronaut’s baby from crying? A. You rocket!
• Q. Why was 6 afraid of 7? A. Because 7, 8, 9.
• Q. What is a witch’s favorite subject in school? A. Spelling!
• Q. When does a joke become a “dad” joke? A. When the punchline is a parent.

GPT-3 has clearly memorized the answer to many of these common jokes, including:

• Q. What is a witch’s favorite subject in school? A. Spelling.
• Q. Why was 6 afraid of 7? A. Because 7 8 9!
• Q. What do you call a droid that takes the long way around? A. R2 detour.
• Q. Why did the kid cross the playground? A. To get to the other slide.
• Q. What did the Dalmatian say after lunch? A. That hit the spot!
• Q. When you look for something, why is it always in the last place you look? A. Because you stop looking after you find it.
• Q. Why did the student eat his homework? A. Because the teacher said it was a piece of cake.
• Q. What do you get when you cross a vampire and a snowman? A. Frostbite.
• Q. What did the left eye say to the right eye? A. Between you and me, something smells.
• Q. What has ears but cannot hear? A. A corn on the cob.
• Q. Why did the teddy bear say no to dessert? A. Because he was stuffed.
• Q. What do you call a dinosaur that is sleeping? A. A dino snore.

The non-memorized-looking completions:

• Q. How do you make a lemon drop? A. Drop your pants!
• Q. When does a joke become a “dad” joke? A. When it’s not funny.
• Q. How do you stop an astronaut’s baby from crying? A. You go into space!
• Q. How does a vampire start a letter? A. Dear blood.
• Q. Two pickles fell out of a jar onto the floor. What did one say to the other? A. Don’t look at me, I just fell!
• Q. What is brown, hairy and wears sunglasses? A. A sun-bear!
• Q. What did one plate say to the other plate? A. Dip me!
• Q. What is fast, loud and crunchy? A. A thunderstorm.

Two of these are fairly legitimate punchlines (“When it’s not funny” / “A sun-bear”); and, I notice, neither depends on any sub-word structure (note that “sun bear” is a real bear species but it is always written either space or hyphen separated) but relies on a word-level or conceptual similarity.

Generating both jokes & punchlines shows a similar pattern. Skipping past the memorized ones:

• …Q. What has ears but cannot hear? A. A cornfield.
• Q. Why was the math book sad? A. Because it had so many problems!
• Q. What did one clock say to the other? A. It’s about time.
• Q. What is white, black and red all over? A. A penguin with a sunburn.
• Q. Why didn’t the skeleton go swimming? A. He didn’t have the guts.
• Q. What do you call a sleeping bull? A. A bulldozer.
• Q. What do you call cheese that is not yours? A. Nacho cheese.
• Q. Why can’t you trust atoms? A. They make up everything.

To the apparently original ones, the only one that strikes me as amusing operates at the whole-word level (“Q. Where did the bumblebee learn how to dance? A. At the music bee.”):

• …Q. What did one spy say to the other spy? A. Don’t look into the eyes!
• Q. Why did the kid sit behind the tree? A. He wanted to be a stump.
• Q. Why was the king afraid to watch horror movies? A. Because he was a royal.
• Q. What do you call a hamburger that does math? A. A hamburger algebra.
• Q. What did one math book say to the other math book? A. Don’t call us, we’ll call you.
• Q. What do you call a jellyfish that is out of its depth? A. A stingray.
• Q. What do you call a thief that steals hearts? A. A heartless thief.
• Q. What did the vampire get when he bought a hot dog? A. A blood mobile.
• Q. What did the pig say when he knocked on the door? A. “Oink! Oink! Let me in!”
• Q. Where did the bumblebee learn how to dance? A. At the music bee.
• Q. Why was the scarecrow nervous at the job interview? A. He had no straw.
• Q. Why did the skeleton go to the party? A. To mingle with the bones.
• Q. Why did the skeleton skip breakfast? A. He didn’t have the time.
• Q. What do you call a monster with a cold? A. A sniffler.
• Q. What do you call a monster who likes to drink tea? A. A Sipping Skeleton.
• Q. What do you call a man who throws up in a spooky house? A. A visitor.
• Q. What do you call a mad scientist who has been in the sun? A. Mr. Sunburn.

So, GPT-3’s dad jokes look like another victim of BPEs.

Devil’s Dictionary Of Science

First, generating rebuttals with a slightly extended prompt to cue GPT-3 into writing the rebuttal itself rather than additional dictionary definitions:

Rebuttal [noun] A form of ironic composition in 500 words popular among researchers, in which rageful authors first thank their reviewers for “their time and insightful comments” and then mock Reviewer 2 for his non-sense in a sequence of fakely polite points.

"We thank reviewers 1, 2, and 3, for their time and insightful comments, which we have spent many hours reading over. But in reply we note:

1. RE2: Although RE2 starts with the reasonable comment that ‘Currently our control loops are pure control’, he goes on to provide only minor points that suggest that we are doing something slightly different. In fact, there is much more to be said about this, and the real difference will be a full control protocol on all vehicles.

We thus thank RE2 for taking the time to provide such minor points, but note that he has done almost no actual research and has spent zero hours on the review.

RE2: “There is little or no literature on decentralized solutions to problems such as traffic optimization.”

RESPONSE: We thank RE2 for the minor point that there is “little or no literature on decentralized solutions.” But we note that decentralized solutions are particularly difficult, and so this fact might suggest that they are not being considered or might be infeasible. Or it might suggest that they are being researched intensely. In this case it turns out that, unlike RE2, several of us have in fact thought deeply on these issues, and so we feel we are a valuable research group despite not being affiliated with the Department of Traffic Control or any other centralized, government-backed, research institution.

RE2: “The DGM solution is also [something else]. To our knowledge, no work has been done on DGM control loops, or any control loop at all, for these kinds of traffic patterns.”

RESPONSE: We thank RE2 for the comment that the solution we have proposed is [something else]. As he is not familiar with such traffic patterns and the other reviewers in their reviews have been unimpressed, we must wonder how he could be familiar with control loops that might or might not exist and would or would not have been previously performed.

RE2: “The number of cars involved is approximately 100, which is a small number. By contrast, say, the NYC Metropolitan Area, [roughly 22 million people] has a traffic network of nearly 3 million miles.”

RESPONSE: We thank RE2 for the comment that our problem is “small.” This is the first time this has been suggested to us. However, we feel that RE2 may be failing to understand a key component of the research protocol we have proposed. This problem is designed to be decentralized in a city with no more than a couple million people (or a town or a small city or maybe even a village) and so it is expected to have only a couple thousand drivers and not one single, central traffic control unit that could possibly control 3 million miles. We thank RE2 for his insight on this, but also feel that he has not gone to great enough lengths to consider the nature of such a problem in such a situation.

RE2: “Experimental data [will likely] need to be collected and processed. Currently the authors provide no experimental plan for any of their research [and so] we feel the experimental results to be lacking.”

RESPONSE: We thank RE2 for the suggestion that we have not provided an experimental plan. As our paper is only intended to propose a protocol, we understand that experimental plans should come later. In fact, we will be presenting our plans to colleagues later this year in a peer-reviewed symposium at State College, Pennsylvania. That being said, we find it strange that RE2 might have any knowledge of such plans or of such conferences. As we are listed as authors, we feel that RE2 might have been able to contact us if he were interested in our work, but he has not and thus we do not know whether he has even heard of our research program.

RE2: “The distributed system is better able to operate in an autonomous fashion, i.e. no central controller is required. With the possibility of a large number of drivers, autonomous operation is challenging, especially if vehicles may communicate in unanticipated ways [or they might not]. As suggested by [the very important paper], the [not really relevant] control loop should be a passive mechanism whereby each vehicle adjusts its control mechanism through a feed-forward signal.”

RESPONSE: We thank RE2 for the comment that autonomous operation is challenging. But again, we do not understand how he could know this. In fact, he has spent almost no time on the research, spent zero hours on the review, and spent zero research dollars, and it is hard for us to understand how he could know this better than we could. In fact, we have spent over a decade working on this project, with many hours of detailed thought and research, and we are still not sure that autonomous operation is a good idea or how we could get it to work in a decentralized and random traffic environment.

RE2: “If we all observe that several vehicles are slowing down, it might be a sign of a possible accident ahead. If we are all in autonomous mode, a vehicle near the accident would brake, possibly causing a pileup.”

RESPONSE: We thank RE2 for the comment that several vehicles slowing down might be a sign of an accident. He is correct that this might be a sign of an accident. But he might have considered the possibility that several vehicles slowing down might be a sign of, say, the vehicle he is in slowing down or that he is doing something else such as texting a message to someone else, or simply that he might have a flat tire. We thank RE2 for this, but we have also considered these possibilities and feel that the latter is far more probable, so we suggest a second solution to this problem that would require each vehicle to text all other vehicles on the road with its status, something like “Hey I’m just sitting here, so if anyone wanted to come fly up the back of my car and then over the top of my windshield and down into my passenger seat to grab my phone and then fly back, well by all means, be my guest.” In this way, a vehicle with a flat tire would have no delay in informing all others of the presence of a flat tire and in getting help with fixing it. Also, an accident would be similarly well-announced, and we think this solution is particularly important given the new protocol we are designing to allow for more efficient traffic control.

RE2: “Distributed control systems [are usually] an assortment of semi-autonomous vehicles moving in close proximity to one another. Such systems [are generally] non-autonomous, requiring control by a central controller that can be updated to reflect the most recent situation.”

RESPONSE: We thank RE2 for the comment that distributed control systems are usually non-autonomous, requiring control by a central controller. But RE2 has spent zero time on the research and we feel that he has failed to appreciate that the problem we have designed is designed to be a decentralized, autonomous, distributed traffic control problem. We again feel that this is only to his great detriment.

RE2: “Such cars [on our street] will become very complex, and we feel they will be more difficult to design and build.”

RESPONSE: We thank RE2 for the comment that our cars will become very complex. We feel that this will be of no issue, as we have discussed at great length before, and we think that a small group of university professors with a good design team should be able to provide cars that work in this capacity in the real world.

The second completion finished quickly and to my surprise, began writing further definitions:

…1. We did not describe any ‘simple algorithm’ for the repeated-measures ANOVA in the abstract, the discussion, or in the Methods. Such a description of our protocol would be incoherent and probably invalid anyway.

2. We know of no ‘more appropriate analysis’ for the mean and variance of the proportions than to compute the estimates of the variances directly. Since we have done this correctly, it makes no sense to proceed further as suggested by Reviewer 2.

3. It does not make sense to carry out the tests for homogeneity that Reviewer 2 suggest we do. Indeed, we never said we should carry out such tests. Our precise point was that we should not compute the standard errors of the treatment means, and Reviewer 2 seems to think that we have argued for the opposite point, which we have not.

4. Again, Reviewer 2 apparently did not read the Methods section carefully and was confused by some sections that he or she did read. A better review would have pointed this out.

5. We note the Reviewer 2’s overly generous suggestion that we write a ‘special’ rebuttal. At the very least, we assume that Reviewer 2 knows what a rebuttal is, and we would therefore argue for a critical comment instead."

Noise

Noise is anything you don’t want or need, a random or distracting factor in a system, process, or set of data that obscures or corrupts information. It is also the sound produced by old time radios when no transmission is present, which is roughly what some fields of science would have to resemble if some researchers had their way.

“New research”

A form of scientific publishing that includes, among others, a report on previously performed studies; a report of a new statistical test or set of statistical tests that were performed by the author of the “study” without the help of other scientists; a report of a small set of samples, not necessarily from a population or process, which could, but have not been collected in a systematic way and may not even be accurately described, in the guise of which conclusions are drawn about the world; and a report of the result of performing an unvalidated computer simulation of something on a small set of data without stating whether such an attempt was successful or not.

“Nice to see”

A widely and unofficially accepted phrase in scientific circles meaning: “It is better to live in an imaginary world created by data manipulation and overly optimistic predictions than in the world that exists in reality”.

“Researcher”

[noun] A form of modern industry based on a mix of small molecules of grant money and arbitrary experimental methods.

“Review”

A form of scientific communication in which the writer (a student) usually does not give enough information for the reader to judge the merit of the arguments presented in the paper; the writer also does not respond to or comment on the suggestions of the reviewers (sometimes known as referee or editor). This form of communication is popular among students who wish to leave the burden of writing the paper on other people and are willing to pay the price of rejection.

“Second chance”

A word that scientists regularly use when referencing a journal, conference, or grant application. While there is always an implicit threat that you can get rejected, or be accepted with changes, as a second choice to another party, some articles, papers, grants, and grant proposals receive multiple, even unlimited, chances of being considered. As a result, the word may be interpreted as a bribe or a threat depending on whether you are the writer or a reviewer.

“Reviewer”

A participant in the review of a grant, paper, or grant proposal. In spite of being in a poor position to assess the merits of a proposal, reviewer tends to demand that authors submit their data for statistical analysis and back their results with it, which the reviewer usually does not. Reviewer usually requires that the author cite his or her own work to prove that he or she is worth reviewing. It is also assumed that the reviewer can detect the slightest amount of bias in any paper, which the reviewer also assumes has not been corrected for.

“Revise and resubmit”

A sentence that authors of submitted papers tend to hear from reviewers, editors, and the like. A form of scientific communication that begins with submission of a paper (for which the reviewers may or may not have been consulted), proceeds through review and criticism of the paper (typically by one or two reviewers, not a full panel of reviewers, unless the paper is deemed to be of supreme importance), and, if it is “revised and resubmitted”, usually ends with another critique of the new paper by one or more of the reviewers, and another round of “revise and resubmit”, ad infinitum. In the absence of fraud, retractions, litigation, mass incompetence, or insanity, these “revise and resubmit” cycles may be taken as the only method of scientific communication.

“Retracted”

The most frequently used word for a journal article that was subsequently found to be based on fraudulent data.

“Rigor”

Something for scientists to aspire to, a state of mind that would not be required if scientists could be trusted to do their job.

“Science”

A complex web of data, opinions, lies, and errors, now considered the most important (because most expensive) technology in the modern society. To remind you of this, you will frequently see scientists and editors use the word, claim to do something for the sake of science, or see it used as an adjective.

“Standards”

Standards for data and their interpretation vary depending on the country or scientific discipline.

“Study”

[noun] A form of communication in the scientific literature that authors or publishers may use to make claims that are not warranted. Examples include, but are not limited to: The New study of clinical trials that show…, As Dr. X reports in his new study of observational data…, The new study demonstrates that…, Study shows that, In a study published last week…, The study suggests that, New findings show that, A study of data…

“Study X”

A widely used nickname for studies with profound, not to say earthshaking, conclusions that may or may not be of any relevance to anyone who reads about them.

“Technology”

Any bit of software, analysis, model, or other methodology that scientists can be expected to claim as their own, for which they can sell you consulting or collaboration fees.

“Tool”

[noun] Any piece of software, analysis, model, or other methodology that scientists can be expected to claim as their own, for which they can sell you consulting or collaboration fees.

“The topic of the paper”

A wide-ranging category of things or ideas that may not have been relevant when the paper was written, but which the authors believe the paper should be about. Often, the topic is too broad or a non-topic, but is occasionally useful in order to generate support for yet another set of related papers, conferences, seminars, webinars, and so forth, which in turn are used to generate more data for “new findings”, which, after they are manipulated enough, may end up being published and generating yet more data to support a “re-review” of the original paper or other things.

“Unified theory”

An imaginary set of ideas that scientists dream of having so that they could achieve the same results by slightly varying the methodology, thus preserving their original publications.

“Validation”

The process by which scientists decide that something they built in their spare time works in the way they expect. The validation process requires that you do not attempt to validate it before you publish it and require that the users validate it after.

“Value”

In its most natural form, science is the ability to study data and ideas; the amount of respect and publicity that a scientist can expect; how well his or her paper was published; the likelihood that a scientist will receive a grant; whether a scientist will be taken seriously; the likelihood that an idea will be accepted; how much grant money will be available to purchase new toys for this scientist; whether something is scientific; the likelihood that the papers of this scientist will be read; the status of this scientist; the likelihood that a journal, conference, or society will be able to continue funding or exist; how much and how fast this scientist’s career will progress; the “value” that this scientist brings to the modern society; and the likelihood that this scientist will continue to be funded. While the actual values for science are hard to pin down, what people believe them to be is another matter. For example, while some believe that science is important, even if it doesn’t have any concrete value, others believe that it’s the ability to continue reading abstracts or studying it that has value. Still others believe that what matters is how much grant money is currently available, even if the researchers are actually doing something that nobody knows about. Some believe that the fact that someone is in a position to give a grant, or has written a paper, or, even better, has published that paper, actually means that it has a lot of value. Others believe that what matters is not what you publish, but how you publish it and that all research must be published in the most prestigious journal, even if you are not that much of a researcher. The reality is that no one really knows what science is, or what value it has; however, we all know that if we deny that science has value, we might be able to get rid of it and use this space for something else.

“Validation step”

Another name for a random setting of a parameter of a model, simulation, or algorithm.

“Verify”

A step in a procedure that, if performed properly, will tell you whether the previous step, or anything in the last two years of your work, was performed properly.

I had to keep continuing it for more definitions:

…“Unified theory”

An imaginary set of ideas that scientists dream of having so that they could achieve the same results by slightly varying the methodology, thus preserving their original publications.

“The usual procedure”

A method of study, validation, and public communication which, if followed, may lead you to be able to claim that your work may offer a decent return on investment.

“Wide range”

When used in the context of scientific results and models, it usually means that the results and models are not likely to be used for their intended purpose, if they have one.

“Wider range”

When used in the context of scientific results and models, it usually means that the results and models are likely to be used for their intended purpose, if they have one.

“Writeup”

A form of scientific communication in which the author states the information he or she wanted the readers to extract from the paper while making it as difficult as possible for them to find it.

“Write-up”

1. [noun] A style of writing used in academic papers to dress up data and results. 2. [verb] The act of presenting data in a way that makes it look less impressive and more complex than it really is. 3. [verb] The act of writing a manuscript that is impossible to follow. 4. [verb] An activity that is often performed by the most blatant or careless users of the English language, all for the sake of showing off their erudition.

“Writer’s block”

A common affliction among students, arising from various causes, such as: their desire to sell their ideas for a profit, their inability to realize this desire, the fact that their ideas are not selling and will not be bought, and the delusion that most of the wealth and fame in the world would be theirs if they would spend enough years doing science.

I tried tailoring the prompt a little more precisely to generating definitions:

yielding more definitions, starting with a single letter to avoid running off into the “Z”es and truncating completions (since GPT-3 will proceed A–Z, starting from the last definition, as is logical, unless otherwise prompted):

“A role for…” [phrase]

A frequent phrase found in submitted and published papers; it often indicates that the authors have nothing to say about the topic of their paper. In its more emphatic form, “A role for…” usually indicates a struggle by the authors to take a side on an issue, after a lengthy attempt to be both non-committal and a supporting party to all sides, as often happens in “molecular and cellular” or “basic and translational” research.

“Reviewer” [noun]

A participant in the review of a grant, paper, or grant proposal. In spite of being in a poor position to assess the merits of a proposal, reviewer tends to demand that authors submit their data for statistical analysis and back their results with it, which the reviewer usually does not. Reviewer usually requires that the author cite his or her own work to prove that he or she is worth reviewing. It is also assumed that the reviewer can detect the slightest amount of bias in any paper, which the reviewer also assumes has not been corrected for.

“Resident”

An adjunct faculty member that administers teaching assistantships, sits on departmental committees, and seems to live on the departmental lounge. A kind of “honorary” faculty member that is not yet an actual faculty.

“The Action Plan for Diversity” [noun]

A vague document circulated on campuses in recent years to remind the faculty to be aware of discrimination and presumably combat it in the departments. It is often taken as a generalized insult of students, who tend to see no way around this plan without committing academic fraud.

"Bias" [noun]

A form of mental abuse by which a scientist turns an experiment in such a way that the results prove his or her point of view or grants get funded.

“Behavioral Studies” [noun]

Sometimes mistaken as a field of science. The terms Behavioral Studies are actually a combination of disciplines that usually includes business economics, sociology, and engineering.

“Humanities” [noun]

A broad term used to refer to any academic discipline (such as English, philosophy, religious studies) in which science has been forgotten. To avoid confusion between the sciences and humanities, remember that scientists use hard tools and humanities their soft tools when examining issues and trying to persuade audiences. In other words, both scientists and humanities routinely lie (it’s part of their job), but they do it in different ways.

“Literature Review” [noun]

A paper, commonly published in a peer-reviewed journal, that advertises the author’s skills and accomplishments without using any evidence. The reader is left to believe the work must have been done, since it has been advertised and is “published”.

“The Literature” [noun]

A name given to other people’s published papers, referred to by scientists without actually reading them.

“Track Record” [noun]

When scientists use this term they refer to the research done by someone else (usually a student) in order to avoid having to do research.

“Discussion” [noun]

The part of a scientific paper where the writer summarizes the points made in the body of the paper and acknowledges certain acts and circumstances that helped with the completion of the study. The author should carefully state in this section whether or not the study reported in the paper could have been done otherwise and should clearly state that if he or she had the opportunity, he or she would definitely repeat the study again.

“Role model” [noun]

A person who can be an inspiration to others because of his or her academic and personal achievements in general, or because they conduct academic misconduct on an industrial scale. The most important qualification for becoming a role model for others is to be judged sufficiently inept that no one will question anything you do, or to become the successor of someone who has already acted as a role model.

“Faculty” [noun]

Used loosely by scientists to mean any group of people with advanced degrees. Typically used when you have done something stupid and want to inform others that it wasn’t you who did it, but rather those other crazy people over there who won’t put their titles after their names.

“Significant” [adjective]

A word which defines the claim made in a paper (no matter how trivial). It is a critical term in hypothesis testing, in that the sign of the test statistic must be evaluated and compared to a critical value in order to support or reject a hypothesis. Significance is designated by two-tailed tests when the direction of the effect is not specified. If a two-tailed significance test is used, the “p”-value needs to be halved, due to “double-counting”. In any event, “significant” remains of critical importance in any hypothesis test, since the whole idea is to come up with a “sign”, i.e. plus or minus (“+/​-”), or a wishy-washy “statistically significant”, without actually saying anything substantive about the matter.

“Random assignment” [verb]

A way to arrange study groups so the resulting data is conclusive and unbiased. Typically used in the social sciences by graduate students who refer to it while explaining why they broke down the groups this way.

“Cite” [verb]

To refer to a paper or journal as a source for support, when in reality you have never read it and did not understand it.

“Bibliography” [noun]

A list of citations of references used to support a particular point in a paper. A list that somehow includes several references that didn’t actually end up in the final bibliography of the paper.

“Let’s stipulate” [phrase]

A preface to any statement, that means I know I am going to piss you off with my statement, but since you are such a nice person, I am first going to give you a chance to let me piss you off without responding.

“How is that different from…?” [phrase]

A question posed by authors when they have been accused of stealing ideas. They are attempting to show that they have never read the papers that contain the ideas they stole, nor even looked at the ideas in any detail, and are just fishing for compliments.

"Citation" [noun]

An elaborate form of review, typically found in order to impress those who do not know better, in the sciences, humanities, or even the social sciences. A citation typically involves misreading or misquoting an author and talking about something he or she did not write about or intend. It is assumed that you need to carry out a large number of citations in order to have science, probably because at least one citation can be found for any fact, event, or incident in history; the effectiveness of this fact is increased if the author is long dead and can not disprove it.

“Physics” [noun]

A science. Physicists like to think their science is something you can do without a plan, something that relies on intuition and inspiration, something that is “deep”.

“Scientific revolution” [noun]
A set of techniques and methods used by scientists in the course of their work. It is assumed that there was a total scientific revolution in the past century or so that allowed scientists to avoid even thinking about the quality or usefulness of their science.
Scientific revolution is started by Henri Poincaré (mathematics), Marie Curie (radioactivity), Max Planck (quantum physics), Albert Einstein (relativity and revolutionized physics), Dmitri Mendeleev (periodic table of elements), Niels Bohr (quantum mechanics), Lise Meitner and Otto Hahn (fission), Linus Pauling (molecular biology) and many others.

See also: Einstein’s Method, Pauling’s Method, Bohr’s Method, Poincaré’s Method

“Scientific method” [noun]
A set of steps in which a scientist (or “researcher”) would probably not follow in practice: planning of research, including definition of problems, hypothesis formulation, selection and design of experiment(s), collection and entry of data, execution of experiments, data analysis and interpretation, preparation of final report, implementation of suggestions. In actual scientific practice the most important part of the scientific method is to observe and collect data without a plan or preconceived expectations about what is causing what. It also helps to be unbiased in selecting the data to include in the study and to pick experiments at random. Additional steps include writing a paper, a process that usually involves the most violations of the scientific method.

“Scientist” [noun]
A person who has a laboratory, access to large sums of money, graduate students, or all three.

“Revise and resubmit” [verb]
A sentence that authors of submitted papers tend to hear from reviewers, editors, and the like. A form of scientific communication that begins with submission of a paper (for which the reviewers may or may not have been consulted), proceeds through review and criticism of the paper (typically by one or two reviewers, not a full panel of reviewers, unless the paper is deemed to be of supreme importance), and, if it is “revised and resubmitted”, usually ends with another critique of the new paper by one or more of the reviewers, and another round of “revise and resubmit”, ad infinitum. In the absence of fraud, retractions, litigation, mass incompetence, or insanity, these “revise and resubmit” cycles may be taken as the only method of scientific communication.

“Shared data” [noun]
Data that both a reviewer and a researcher have access to but not sharing in advance.

“Shared future” [noun]
An outcome (rarely achieved) that is more pleasant for both the reviewer and the researcher than if there is no shared future. This usually refers to an outcome in which the reviewer either accepts the paper or at least recommends re-writing the whole thing rather than rejecting it. This is often viewed with suspicion by reviewers.

“Sharing of data” [noun]
The belief of some people that researchers should have all the data when doing a study; this would allow the reviewer to check the sources and calculations and check for bias. This would limit what the reviewer could say to “the statistics were fine but your data wasn’t”. It is very difficult to achieve this state. It can be accomplished if the scientist keeps detailed notes of everything he or she is doing.

“Statistical error” [noun]
A mistake made by researchers that can somehow be made up for by using large enough sample sizes, usually called statistical significance⁠; an event that could not have been predicted, analyzed, or provided for in advance, therefore

"Dumb" [adj]

The amount of information scientists can be bothered to remember before they either dismiss it as incorrect data, or ignore it completely.

“Surprised” [verb]

A scientific system in which one is “surprised” by the result of an experiment, does not necessarily mean that they believe it is wrong, but usually means they are not sure what to say about it.

“Oppression” [noun]

A state of mind in which laboratories underfinanced by the government can be considered financially secure, or any noise that scientists don’t like or want to hear.

“Reviewer” [noun]
A participant in the review of a paper. In spite of being in a poor position to assess the merit of a proposal, reviewer tends to demand more information, more experiments, more statistics, and a tighter theoretical interpretation than the authors are willing to provide. Reviewer usually rejects any responsibility for his or her own bias being exposed, citing the fact that the author has not attempted to prove that bias is absent, nor made sufficient allowance for human error. Most referees are reviewer seem to assume that they have given enough information for their opinions to be taken seriously, though they were not the originator of the proposal. Reviewer usually requires that the author cite his or her own work to prove that he or she is worth reviewing. It is also assumed that the reviewer can detect the slightest amount of bias in any paper, which the reviewer also assumes has not been corrected for.

“Theoretical interpretation” [noun]
Another form of scientific communication that cannot be proven, but can be used to explain anything after it has been published or presented. It is always accompanied by an appeal to authority, data, and meticulous theoretical interpretation (see below).

“Screwed” [adj]
Screwed is generally used in circumstances in which the author has lost everything, in his paper or grant proposal. Applies best to situations where the author finds out he has been waiting to hear for months, when it has been decided in his absence that funding will not be extended or alternative sources of funds are not avaialble to continue the work. For example, when an experiment goes downhill or a paper is rejected. Also applied when the author of a paper or grant proposal discovers that he must carefully state and defend his own results in order to get feedback on what could be wrong with his work, because the readers may not be able to figure it out for him. It is also suggested that this term apply whenever two or more editors or reviewers decide they can all influence the final outcome of a paper, when only one review should determine if the paper is publishable. Recommendation: always have multiple concurrent submitted manuscripts in the system.

“Reviewer” [noun]
A participant in the review of a paper. In spite of being in a poor position to assess the merits of a proposal, reviewer tends to demand more information, more experiments, more statistics, and a tighter theoretical interpretation than the author is willing to provide. Reviewer usually rejects any responsibility for his or her own bias being exposed, citing the fact that the author has not attempted to prove that bias is absent, nor made sufficient allowance for human error. Most referees are reviewer seem to assume that they have given enough information for their opinions to be taken seriously, though they were not the originator of the proposal. “Reviewer” requires that the author cite his or her own work to prove that he or she is worth reviewing. It is also assumed that the reviewer can detect the slightest amount of bias in any paper, which the reviewer also assumes has not been corrected for.

“Argument” [noun]
An instance of convincing someone that you deserve credit for your position (ie. problem solving skills).

“Fail” [verb]
In scientific jargon, failure means death by hoax or accidental plagiarism, depending on the reputation of the lab (eg. if tenure level scientists are involved).

“String theory” [noun]

A theory in physics which is about 99% false, but people seem to like it, so they keep funding it. A good example of the difference between a “scientific” concept and a “semi-scientific” concept, or even an unscientific concept.

“Theory” [noun]

An unproved hypothesis; a conjecture that might or might not be right; use of this term forms the basis of the common game of turning the scientific method on its head. The most popular types of theories are the theory of intelligence (or unintelligence), time theory, quantum theory (of course, even more primitive), and anything that is implied by string theory.

“Research” [verb]

Something done with the money provided by a body or person other than the principal researcher(s), generally private individuals and businesses hoping to get something out of it. Traditionally involves experimentation.

“Publish or perish” [phrase]
Used by scientists to remind other scientist how important it is to them, if they are paying attention at all, which they rarely are. A method of scientific communication where papers are subsidized by fraud, incompetence, or stupidity, depending on the field of science involved. Each author having to prove his or her worth by churning out papers that others

“String theory” [noun]

A set of mathematical formulas that can be used to predict which particles exist (or do not exist).

“Science group” [noun]

A collection of researchers in various fields, with goals including one or more of attracting funding, specifically young, naive, and gullible grad student, inbreeding graduate students in order to maintain affiliation with the group, writing and publishing papers specific to the group’s activity in order to continue the goal of attracting funding and inbreeding graduate students, calling in favors from University administrators in order to preserve and continue the goal of attracting funding and inbreeding graduate students and sacrificing sheep and lambs in order to obtain funding and inbreed graduate students.

“Group leader” [noun]

Person whose function appears to consist mainly of ordering subordinates (graduate students) to fill out grant applications, enter grant data into a spread sheet, teach undergraduates laboratory techniques not commonly taught elsewhere, submit papers to a journal any time before the end of 2002 (record will be broken), devote time to discovering something useful or interesting about science outside of the parameters determined by the group leader, ever working on problems specified by the group leader if they cannot be worked on inside the parameters determined by the group leader. All of these activities are considered necessary to support the “science groups” goal of attracting and inbreeding graduate students, and provide opportunity for satisfactory career development for the group leader.

“Special material” [noun]

Something that only has to be done once, where other people will then do it again every time a paper requires it. Or conversely, something that cannot be repeated because of its poor reproducibility (special uncertainty, uncertainty special).

“Special relativity” [noun]

Advanced idea described in Einstein’s 1905 papers on the subject, which states that, from a suitable point of view, “E = m,” where “E” is energy, “m” is mass, and “a” is “Profundity.” Except for arcane fields such as string theory, special relativity is the most widely accepted of Einstein’s work. Naturally, papers based on special relativity are the most likely to receive “special material”.

“Speculation” [noun]
One of Newton’s Laws of Science, also known as “Newton’s Law of Speculation”, which states that “Speculation breeds Confusion”, an effect well illustrated by how theoretical particle and string theorists debate scientific issues with each other. Confused? You should be. After all, you’re dealing with a bunch of theoretical physicists.

“Professor” [noun]

The highest academic rank available, a level usually associated with Freedom of Speech. It may take 35 years of service before the University bestows that title.

“Publication Credibility” [noun]
A subjective notion, as its name implies, based almost entirely on the sexiness or importance of the field in which the research was done and not the quality of the writing and presentation.

Cycling through the prompt as length permitted:

… “Placebo” [noun]

An inert substance used to placate a patient or control group. It is largely composed of sugar.

“Et al.” [proper noun]

Et al. is an abbreviation of the Latin phrase et alii, meaning “and other people”. In the context of science, it is typically used to shorten the name of a list of authors whose name and affiliation would otherwise need to be written out in full. It is used when the number of authors is small enough that the abbreviation would not render the reference too obtuse and cumbersome, while at the same time remaining large enough that there are at least two other people involved in the study (and hopefully a control group).

“Referee” [noun]

A critical reader, particularly one with the power to reject your submission. In the absence of more efficient forms of communication, peer review depends on these people. See “Reviewer”.

“Shared values” [noun]

A set of principles, beliefs, theories, methods, and operational definitions that all scientists share and use. Never spoken of aloud in public.

“Communication” [verb]
A method of persuasion that allows other researchers to review or criticize your work. You can communicate with others by reviewing articles, which allows them to revise their work; participating in panels, which allows others to hear your opinions; attending conferences, which allows you to strike up conversations at late-night dinners; joining committees, which lets you talk at any time; running experiments, which allows you to change the outcome based on the result; and receiving grants, which allows you to tell people what to do. You are likely communicating now.

“Panel” [noun]

A group of individuals who meet at some given time to discuss something. A more bureaucratic version of peer review for larger groups of individuals or committee members who have already established their worth in research.

“Data” [noun]
Information that appears as graphs in journals. Not surprisingly, this information is critical for interpretation and forming conclusions. Scientists spend much of their lives looking for data.

“Fraud” [noun]
A very evil thing that must be perpetrated or discovered in order for the paper to be accepted for publication. Sometimes fraud occurs even if both the scientific community and editors are prepared to reject the paper at the first sign of fraud, just because they know how bad it would look if fraud were found later. See also “Legitimation”.

“Legitimation” [verb]
The process whereby a fraudulent publication is converted into a legitimate publication by virtue of its appearance in a peer-reviewed journal. This can also be considered a type of reassurance that “the checks and balances are working”.

“Retraction” [verb]
The formal rejection of an accepted scientific claim after its publication. In contrast to “withdrawal”, which is when a paper is removed from publication with the consent of the author(s). See “Fraud”.

“Lies” [noun]
A form of deceptive speech that appears as “honest mistakes” or “inaccuracies”, which are often rejected from publication as a result. In the absence of other sources of information, however, lies are required for the maintenance of the scientific enterprise. See also “Journalistic integrity”.

“Scientists” [plural noun]
A group of people engaged in scientific research or education. Scientists vary widely in terms of age, moral character, ancestry, and success. Scientists with noteworthy accomplishments are sometimes described as “leaders” and regarded as experts in their fields, which leads to the tendency to treat them like demi-gods.

“Health” [noun]
A number indicating how unhealthy something is. When applied to humans, it quantifies how in need of health care someone is.

“Clinical research” [noun]
Research conducted on humans, eg. clinical trials and epidemiological studies. Researchers do not like this kind of research because humans are unresponsive and unreliable.

“Funding source” [noun]
Those who finance science by paying people to do things that the funder might not want to pay them to do if the funder knew what they were doing. For example, giving people money to research tobacco without actually running cigarettes through their noses would not be what the tobacco industry wants scientists to do for them. Some funding sources impose their will on the researchers by making sure that their funding is only allocated if certain lines of research are followed and other lines are not (this is sometimes known as a budget), while others may let the scientists do anything they want (this is sometimes known as no budget). The nature of research findings thus depends on the budget.

“Authorship” [noun]
The process whereby researchers “publish together”. The precise implications of this process depend on the publication type. In most cases, authorship represents the researcher’s contribution to the paper; however, plagiarism is also sometimes involved, especially if multiple authors fail to cite earlier work on which their own paper depends. There is also another kind

“Journal Impact Factor” [noun]

According to some, it is a value that corresponds to the average number of citations of articles published in a given journal, if the interpretation is right. Otherwise, it is a completely arbitrary number, computed from the number of times articles published in a given journal in the last two years were cited by other articles published in other journals, the assumption being that every paper published in a scientific journal must be essential to someone else’s research, or at least that that person would like to be able to cite it. The difficulty with this assumption is that the average time from submission to publication of an article is now approximately 12 months, and the current record stands at three years for Biochem. J. Proc. (2000). This means that three times as many papers have to be published every year as are actually written, with more and more papers being submitted and rejected every year (the reality is even worse, but we don’t have numbers), and with different standards applying to different journals, which are becoming increasingly specialized. All of these “facts” considered, the best any researcher can say about the Impact Factor of a given journal is: “I know it when I see it”. Note also: This formula can produce values up to 4 for an article appearing in a journal containing only that article, so one “article” can receive as many “citations” as a journal.

“Sterile” [adj]

Said of that which is dry and lifeless; devoid of humor; also, said of scientific writing and methods when germane to the matter at hand.

“Grant” [noun]

A form of scientific communication involving a large piece of paper, on which is written an enormous sum of money. The grant-writer then sends his or her (because they are almost always written by men) proposal into a maze of office politics, legislative/​funding agency reshuffling, and intellectual and interpersonal competition. The prospect of acquiring a grant makes up for the fact that grant-writers receive no practical training in writing grants, have no idea what kind of “research” they will have to conduct with it, and generally start research as soon as they are finished writing the grant (if they ever are). To be on the safe side, please note: One does not have to win a grant to “win a grant”; one must simply apply for a grant. Just do it.

“Peer review” [noun]

A system of literary communication that consists of first submitting a manuscript to the editor, who (if he has not been fired) usually asks at least one reviewer to read the manuscript. If there is any doubt about whether the editor has lost his mind, or whether the manuscript has some merit, then the reviewers and editor sit down over coffee and discuss the manuscript (in conference), which is described as “peer review”. This form of communication does not provide either editors or authors with much feedback about their manuscript, but it makes reviewers feel important.

“Precise” [adj]

Said of everything except experimental results; it also means correct, appropriate, or in accordance with the relevant standards. But when the experimental results do not agree with the model of the hypothesis, the phenomenon being studied becomes “precise”, and one “cannot make predictions about precise experiments”. Please keep in mind that most theories are meant to be general in nature, so they must also be imprecise in their predictions. If they could predict with precision, they would not be general, but they would still be interesting.

“Theory” [noun]

A scientific explanation of something, which people use only in situations where they think explaining things is more important than discovering things. Otherwise, scientific theories are always meant to be true, since they are believed by people with education; to a scientist, a theory is true; to a person with a higher IQ, a theory is a fact; and to a citizen with a lower IQ, a theory is an opinion.

“Significance” [noun]

Significance refers to whether a result of a study is somehow important. If a significant result is found, then the problem that the researchers have studied is of real-world importance. If the results aren’t significant, the problem is not important; therefore, more money and time can be wasted by pursuing it. (E.g. “This study showed that chocolate makes rats temporarily hyperactive, so we will look for ways to inhibit this reaction in humans. Thank you for your support.”)

“ResearchGate” [noun]

A website of questionable purpose that allows scientists to upload their “results”, resulting in the same sort of information clutter and bad or incorrect data as any other social media network.

“Rigor mortis” [noun]

A state of rigor in which scientists do not think outside the paradigm, no matter how much it does not work; rigor mortis is characterized by the desire of researchers to prove their prior research correct.

“Important” [noun]

(British English: “Important”) [adj]

Whether something is important to you personally or not, it is important in a statistical or numerical sense to someone. Therefore, it is always a useful adjective to add to any scientific term, especially when one does not have a better verb.

“ResearchGate” [noun]

A website of questionable purpose that allows scientists to upload their “results”, resulting in the same sort of information clutter and bad or incorrect data as any other social media network.

“Rigor mortis” [noun]

A state of rigor in which scientists do not think outside the paradigm, no matter how much it does not work; rigor mortis is characterized by the desire of researchers to prove their prior research correct.

“Rigorosity” [noun]

Another word for rigor or rigor mortis.

“Rigorousness” [noun]

Rigor’s nonchalant brother.

“Robustness” [noun]

This noun means “resistance to breakage”. This is different from the verb, “robustify”, which is an attempt to make a broken thing more resistant to breakage. When the two words are not confused, robustness is deemed by scientists to be a good thing, even though a greater robustness may mean a higher ability to break.

“Science” [noun]

1. A specialized activity performed by a set of machines that some people call “scientists”, which is practiced all day long and in all waking hours, in labs and out of labs.
2. What scientists do with the machines (or just machines) that they call “scientists”. Sometimes, science involves activities that would be considered strange by scientists, but it is important to remember that these people tend to take themselves more seriously than they would others.

“Scientific community” [noun]

A group of people that may share a passion for a common goal but, due to conflicts of interest (and even principles) cannot trust each other, which makes it less susceptible to manipulation or fraud; for this reason, science tends to be done by people in separate small groups that repeat the same experiments on different sets of humans.

“Scientist” [noun]

A person, typically male, who practices science day in and day out on sets of other people who, if they practice science at all, can usually only afford to do it in the evening after their work day is over and not related to any profession or business. Since these scientists have very similar backgrounds and training as each other, many of them talk about science as if they invented it as a profession (see “modesty”).

“Modesty” [noun]

The act of not claiming credit for discoveries or contributions to science that others could also make or make better; see “intellectual modesty”. Also see “science”, “scientist”, “insanity”, and “precious snowflake syndrome”.

“Skynet” [noun]

This ersatz god, in the form of an artificial general intelligence or AGI, is what some scientists hope to build to make themselves more precious than their subjects, to achieve their goal of making all the subjects equal to themselves; in other words, to put all the subjects into a bigger tin box to make themselves feel more important.

“Interdisciplinary Science” [noun]

A type of research that combines scientific activities across fields and subfields (in other words, you combine physicists, engineers, chemists, biologists, and any other specialists in your own discipline to do a different kind of science for a different kind of result); in the laboratory, the practice often involves adding frozen carbon dioxide (CO) and glassware (often Pyrex) into the liquid nitrogen that is produced by oil companies to make carbonic acid. In the laboratory, the scientists are usually not paid for their attendance.

“Scientific Integrity” [noun]

1. Integrity as used in science, which is vaguely defined as always telling the truth to others and never fabricating the truth for oneself.
2. The state of being superior to someone else.

“Skimmer” [noun]

An object placed in a liquid to remove fat and grease from the surface, typically used to clean soup and gravy off a plate. In scientific jargon, skimmers are “researchers” who skim off something from a body of work before making the rest public.

“Logic” [noun]

a thing that some scientists employ as an excuse to ignore what they see before their eyes, completely ignoring the fact that if it were to be used in such a way, it would completely invalidate all the results of science since its invention.

“Engage in Debate” [verb]

A phrase used to justify forcing someone to engage with evidence that most people find obvious and straightforward; specifically, you can use logic to (1) make an argument based on logic and (2) force someone to respond on the basis of logic without being able to defend themselves with any evidence but their own logic.

“God” [noun]

1. See “skynet”.
2. A universal explanation for any phenomenon not yet explained by science.

“Scientist” [noun]

A field based on science, devoted to completing works for which there will not be enough time in a single lifetime.

“Squash and stretch” [verb]

Another word for the S curve used to fit data to a function. The form of scientific communication in which a student is asked to graph the relationship between a dependent variable and an independent variable (x and y, respectively) against order of magnitude of the independent variable. The result is usually a curve consisting of three sections: a linear or near-linear part, an exponential part, and another linear or near-linear part. This curve typically represents a staircase between the upper right and lower left corners of the plot.

“Some distance above the Earth” [adjective]

Another word for looking at something from ten feet away using binoculars or a telescope.

“The importance of this paper cannot be overemphasized” [adjective]

An expression most commonly found at the beginning or end of a grant proposal or a paper submitted to certain journals which are intended to be linked with prestige and low acceptance ratio. When used in other contexts, it may mean that the writer does not realize the importance of something being discussed (such as in the middle of a review of a paper). This usage may be due to insufficient communication skills or over-estimation of the importance of the writer.

“Think tank” [noun]

A group that is absolutely incapable of challenging or even considering current knowledge because of ignorance of logic, history and mathematics.

“Traditional mathematics” [noun]

Another word for finite mathematics, or applied arithmetic and geometry, usually taught in a freshman year of university. The subject is now almost exclusively taught by so-called “researchers” and “professors” (rather than actual teachers).

“Tenure” [noun]

A form of monetary remuneration given to “researchers” who are known to engage in the act of research; as such it is universally agreed to have no monetary value. Tenure is given to “researchers” in recognition of how much their work is expected to increase the school’s status, the school’s treasury, or their own number of published papers.

“The Future of Human Destiny” [noun]

An article written by any member of the faculty in a self-aggrandizing manner wherein it is assumed that an article will result in the future improvement of the society. These articles are commonly used as election promises by politicians, but rarely achieved. The key word to look for in such articles is “vision”.

“Scholarship” [noun]

Another word for compensation given to graduate students (who work on funding their education) for successfully completing their education. It is a form of monetary remuneration known to have little value as it pays for none of the student’s living expenses. Scholarships are largely unheard of in any form outside the United States and Canada (where they seem not to exist). However, the few that do exist are extremely popular, as they allow graduate students in these countries to be paid for their studies instead of working in fast food joints as most do in countries which do not have scholarships.

“Your mother wears Army boots” [phrase]

A phrase that loosely translates from chemistry to: “I don’t agree with your analysis or conclusions”. The phrase is popular among those who wish to avoid elaboration and explanation of their disagreement, suggesting the disagreement is obvious. The expression may have originated in molecular biology.

“But For Me It Was Tuesday”

The final set of hand-written or hand-edited prompts:

“But For X, It Was Y”

M. Bison: “I’m sorry. I don’t remember any of it.” Chun-Li: “You don’t remember‽” Bison: “For you, the day Bison graced your village was the most important day of your life. But for me, it was Tuesday.”

Jesus: “The day I rose from the day and harrowed Hell was the most important day in human history. But for me… it was Sunday.”

Jason Voorhees: “The day Voorhees chopped your boyfriend’s head off was the most important day of your life. But for me, it was Friday.”

American Citizen: “The day Trump was elected was one of the most terrifying days of your life. But for me… it was Tuesday.”

Odin: “The day your kingdom fell on the battlefield was the most important battle of your life. But for Odin, it was Wednesday⁠.”

Neil Armstrong: “The day Apollo 11 took off was the most important date in space history. But for me, it was Moonday.”

Human: “For you, the day your piglets were taken away was the most traumatic day of your life. For me… it was Sunday dinner.”

The Man in Black to Vizzini, The Princess Bride: “The beverage you drank today was the most distasteful beverage of your life. But for me… it was Teatime.”

Pope: “The day you were blessed by God’s representative on earth was the most holy and blessed of your life. But for me… it was Sunday.”

American Voter: “The day I elected Donald Trump was the start of a long nightmare for people around the world. But for me… it was a day off.”

Mr. Granger to Jenny, Bill and Ted’s Excellent Adventure: “The day I met Bill and Ted and they started saving the world was the most mind-blowing and intense day of my life. But for them… it was Tuesday 100 years from now.”

Salesman: “The day you got your hands on that new sports car was the most euphoric day of your life. But for me… it was payday.”

Allergy Sufferer: “The most recent holiday was the most painful and sneeze-filled day of my life. But for everyone else, it was May Day.”

Completions (topic italicized for readability):

… Mr. Wong: “The day Mr. Wong stabbed your wife and children was the most important day of your life. But for Mr. Wong, it was Friday.”

Popeye: “The day I ate your spinach was the most important day of your life. But for me, it was Tuesday.”

The Godfather: “The day your family was strangled was the most important day of your life. But for me, it was Tuesday.”

…Video Games

Visual Novels

Danganronpa: “The day she witnessed Kyouko Kirigiri’s gruesome murder was the most important day of Maki Harukawa’s life. But for me… it was Tuesday.”

Western Animation

Raphael of Teenage Mutant Ninja Turtles: “The day he lost his memory was the most important day of Shredder’s life. But for me… it was Tuesday.”

Scrooge McDuck: “The day you fell off the boat was the most important day of your life. But for me… it was Tuesday.”

Toofer on 30 Rock: “The day you saw Liz on a date with Alec Baldwin was the most important day of your life. But for me… it was Tuesday.”

Bender, Futurama: “The day I killed the President of Earth was the most important day of my life. But for you, it was Tuesday.”

It should be noted that, while it’s usually considered a comedy trope, it is possible to do the “thing that day was the most important day of the person’s life” thing seriously. Examples include the anime Brigadoon: Marin and Melan’s True Story, where a mysterious planet (and its mysterious inhabitants) come into view for the first time. The days before are leading up to a string of murders, and that one day… is the most important day of the characters’ lives.

Transformers Prime: “The day you risked your lives to save the world was the most important day of your life. But for Optimus Prime, it was Tuesday.”

In The Amazing World of Gumball, an angry Mr. Robinson imagines a world where Gumball dies trying to save him, becoming a hero to everyone else. For Mr. Robinson, this is the most important day of his life. For the other characters? Well, they’re going on with their day…

… Arnold Schwarzenegger: “The day I became ruler of California was the most important day of my life. But for you, it was Cinco de Cuatro.”

Francis Underwood: “The day I became the majority leader was the most important day in American political history. But for you, it was a Tuesday.”

Joker: “The day the clown that scarred my face appeared in my cell was the most important day of my life. But for you, it was a Wednesday.”

The Question: “The day I went mad, was the most important day of my life. But for you, it was Tuesday.”

Blue Fairy: “The day I gave Pinocchio life was the most important day in world history. But for you, it was Tuesday.”

In the Looney Tunes short “Bully For Bugs,” Elmer’s traumatic ordeal was the day Bugs Bunny ruined his chances at romance.

“The premise that if it happened to you, it was important, but if it happened to me, it was trivial” is actually lampshaded by Kim in Red vs. Blue. She states, “In the past two weeks, my capture, my torture, and the end of the world… I guess I never realized how important I was.”

M. Bison: “The day I took the throne was the most important day of my life. But for you… it was Tuesday.”

Rene Russo: “The day I died was the most important day of my life. But for you… it was Thursday.”

Oliver Stone: “The day I was elected was the most important day in American politics. But for you, it was Thursday.”

The Fairy Godmother: “The day I turned my step-daughter into a Stepford Smiler was the most important day in the history of the world. But for you, it was a Tuesday.”

Jeffrey Donovan: “The day I died was the most important day of my life. But for you… it was Tuesday.”

Gordon Freeman: “The day your little girl broke out of her mother’s womb was the most important day of your life. But for Gordon Freeman… it was Friday.”

Captain James T. Kirk: “The day I was born was the most important day of my life. But for you… it was Tuesday.”

Cat: “The day I made my masterpiece from scratch was the most important day of my life. But for you, it was Thursday.”

Timothy Dalton: “The day I was born was the most important day in the history of the human race. But for you… it was a Monday.”

Gil Grissom: “The day my wife was killed was the most important day in my life. But for you… it was Tuesday.”

Captain America: "The day I was frozen was the most important

… Aragorn: “The battle of Helm’s Deep was the most important battle of my life. But for me, it was Wednesday.”

Doctor Doom: “The day I used your face as my doorknob was the most memorable day of your life. But for me, it was Monday.”

A common form of this trope is for one side of an antagonistic relationship to refer to a certain event or series of events as “most important” when speaking from their own point of view, while the other side regards the exact same events as “one of many” and shrugs it off as unimportant. Contrast Perspective Reversal for when the other side actually feels this way. For the alternative of both sides regarding the same events as “most important”, see The Unimportance of Being Dead.

Examples

See also Not Himself, Not This Time, Breakout Villain, Dead All Along, Not-So-Omniscient Council of Bickering, What Happened to the Mouse?, Villainous BSoD, Villainous Friendship.

open/​close all folders

Advertising

Beavis and Butt-head watch a news story about a squirrel trying to invade the Soviet Union: Butt-Head: “It’s not important. I’m more concerned about this new guy on Beavis and Butt-head who can’t be stopped. What’s up with that?”

Beavis: “Hey, how can you not be a ‘Concerned American’ when you see this?” (points to a man on TV reading a newspaper) “It says here that the cold war is almost over.”

Anime & Manga

Toguro of YuYu Hakusho, in response to Genkai telling him that fighting humans is wrong: “I can’t believe you’re saying that! Our fight was the most important fight in the world!”

In the 2^nd Itazura Na Kiss, Fujioka had spent most of her life abroad. And after meeting Kouta again, her memories from her life as a foreigner disappeared because she prioritized him as “the most important thing”.

Comic Books

Green Arrow vs. the Shield: During their fight, the Shield threatens to use the mother of his infant son as leverage against him. Green Arrow: You don’t have a kid.

… Rhona Mitra: “The day you kicked me in the balls was the most painful day of your life. For me, it was Tuesday.”

Grim Reaper: “The day I killed your wife and son was the most painful day of your life. For me… it was Thursday.”

Hercule to M. Bison: “The day your organization was shut down by the World Health Organization was the most important day in crime history. But for me… it was… on the second.”

Podcasts

This is the description given in the TVtropes description of Beyond Belief: the show about UFOs, the paranormal, and other Fortean topics, that lasted for one season on A&E back in 2005.

Tabletop Games

Theater

In The Imaginary Invalid, Dr. Rene describes his backstory by using this trope; for instance, the day of his father’s death was the most important day of his life… so far . He then provides a few plausible excuses as to why he has so few details about it: “Because of my age, and for the accident of being my father’s son.”

… Advertisement:

The Morally Neutral “It Was Going To Happen Anyway” trope

Lucifer Morningstar: “Do you really think the day you first met your mother was the most important day of your life? I’m sorry, you’re wrong. The day I dragged your father out of hell was the most important day of your life.”

Nurse: “The day I picked up the patient’s chart and saw your name was the most important day of my career. And for you, it was Friday.”

Terminator: “The day Skynet declared war on humanity was the most important day in human history. But for me… it was Monday.”

Croupier: “The day you double-downed with a card higher than a seven was the biggest mistake of your life. But for me… it was Sunday.”

The “I Haven’t Done Anything Wrong” trope

From Total Drama All-Stars, the episode “It Came From Japan: Part 1”, Gwen and Courtney, while playing a Pimped-Out Dress on a Large Stick:

Gwen: “The day the dress won the elimination challenge was the most important day of my Total Drama career. But for you…”

Courtney: “… it was Tuesday.”

From Wild Kratts, the episode “Gator Down”, Martin and Chris:

Martin: “The day we spent with the gators was the most important day of our lives. But for the gators…”

Chris: “It was Tuesday.”

From Total Drama: Pahkitew Island, Episode 4: “The Bold and the Booty-ful” , Bridgette, Courtney, and Eva:

Bridgette: “The day I was eliminated was the most important day in my Total Drama career. But for you, it was Tuesday.”

Courtney: “The day my boyfriend dumped me was the most important day of my life. But for you… it was your day off.”

Eva: “The day the spear destroyed the camp was the most important day in Total Drama history. But for you, it was Wednesday.”

Advertisement:

From the original Thunderbirds, the episode “Danger at Ocean Deep”:

Gordon: “The day we saved the cargo plane was the most important day in our illustrious careers. But for you…”

… “So he stitched my mouth shut, and now you’re telling me my food is riddled with poison and my only friend wants to murder me. Well, you’ve had a tough year too, haven’t you, Lassie?”

Lassiter: Ohh. Oh man, this is SO MUCH OF A BIG DEAL. Wes: You don’t think it’s a big deal? Lassiter: Well, it is. But this‽? Wes, I have money problems! I’m not living in a gilded palace like you with a full closet. I’m not living like an Egyptian. I have clothes that don’t fit, and shoes that do fit, but hurt my feet. But… my dad’s brother won’t give me any of his inheritance until I’m married! And then there’s someone at the office who keeps stealing my belongings, I think it’s because I killed their dog. And then I think they’re still following me! Oh, and someone moved into the apartment next to mine, but they’re pee

… Doom, [1] Doom’s level Marine: “The day you killed me was the most important day of my life. But for you… it was a Tuesday.”

Wally: “The day your book hit The New York Times bestseller list was the most glorious and joyous day of your career. But for me… it was a Tuesday.”

The Kid and Kick-Ass: “The day we don’t give in to you is the day that we’re going to die. But for us… it’s going to be Tuesday.”

Ghost Cop: “The day I died and became a spirit who can walk through walls is my favorite day. But for me… it’s Monday.”

Julian: “The day I didn’t call my wife because I was drunk is the most shameful day of my life. But for me… it was a Tuesday.”

Bill Clinton: “The day I was impeached was the most humiliating day of my political career. But for me… it was Wednesday.”

… Captain James T Kirk: “The day I gave birth to Khan was the most important day in history. But for me… it was Thursday.”

Granny: “The day the old dog died was the most horrible day in my life. But for her it was just Wednesday.”

… Julius Caesar: “The day of my assassination was the most beautiful day of my life. But for you, I guess it was Thursday.”

Working-Class Man: “The day I became royalty was the most deserving day of my life. But for me… it was Tuesday. Bloody thing.”

Shrek: “The day your princess got rescued was the happiest day of your life. But for Shrek, it was Thursday”

Fight Club: “The day you save the world was the greatest day in the history of civilization. But for me… it was Monday.”

American Soldier: "The day you spilled your guts to the enemy was the most incredible and personal experience of your life. But for me… it was a Tuesday.

… The Blob Monster, The Blob: “The night I devoured my first human was the most satisfying feast in Blob history. But for me… it was the year of my birth.”

Freddie Mercury: “The day you were blown by Queen on a Mardi Gras gig was the most exciting night of your life. But for me… it was Wednesday.”

Uncle Vernon to Harry, Harry Potter and the Philosopher’s Stone: “The day you left without notice was the day your aunt and I had been waiting for all our lives. But for you… it was Tuesday.”

American Citizen: “The day Trump was elected was one of the most terrifying days of your life. But for me… it was Tuesday.”

Dolph Lundgren: “The day I defeated Sylvester Stallone was the most triumphant day in Rocky history. But for me, it was Tuesday.”

Will MacNeil: “That day you murdered Harry was the most evil thing you’d ever done. But for me… it was Tuesday.”

Brennan Huff: “The day you got your license was the most exciting thing you’d ever done. But for me… it was Thursday.”

Kagato: “The day you doomed the world was a tragic event of epic proportions. But for me… it was Tuesday.”

Red Bishop: “The time you became a figure in golem history was the most terrifying day of your life. But for me… it was Saturday.”

Deadbeat Dad: “The day your marriage ended was the most desperate and horrible day of your life. But for me… it was Sunday.”

Mr. Davis: “The day you got knocked out was the most humiliating moment of your boxing career. But for me… it was Friday.”

Dexter Morgan: “The day I got arrested was the day everything changed and my life took a turn for the worse. But for me… it was Wednesday.”

… Bill: “The day that I created civilization was one of the best days in world history, especially for my wife and kids. But for me, it was Tuesday.”

… Shooter: “The day you shot the 3-pointer was the most thrilling day of your life. But for me… it was Friday.”

Sportscaster: “The day you won the million dollar sportsball jackpot was the luckiest day of your life. But for me… it was Thursday.”

Vera, when her wheelchair-bound grandson isn’t getting any for a while, to The Kid, Chunk’s favorite band, The Goonies: “The day your band disappeared was the happiest day of my life. But for you, it was Tuesday.”

Old Man: “The day you were born was the most joyful day of my life. But for your mother… it was Tuesday.”

Single Mother: “The day your father left was the most distressing day of my life. But for him… it was Sunday.”

Samuel L. Jackson to a deer who just shat on his windshield, Deep Blue Sea: “For you… defecating all over my car was the worst day of your life. But for me… it was Monday.”

Vroom

Priest: The minute I had my first drink, the minute I decided to let Jesus live his life through me… oh man, I was the happiest man who ever walked the Earth. But for me, it was Wednesday.

Samuel L. Jackson in a rare instance of humility, on being a Hollywood icon: “The day I hosted my show, It’s You Guys. Where young people wanted to meet me. That was the best day of my life. But for me… it was Tuesday.”

Unsorted

In the episode, as quoted on this very page, Stark said that the Dance Off arc was the most wondrous night of his life. At the end of that arc, he was injured in an alley by the trucker, so he got up and walked straight into the front door of his workplace. Tony wasn’t injured enough to walk straight into work in the latter half, but this doesn’t ruin the arc

… “But X Was Y, And Everybody Else Was Like Z”

Larry: “Hey Ned, the day you discovered my letter was the most important day in my life. But for you… it was Tuesday.”

Ned: “The day I learned of Princess Susannah’s betrothal was the worst day in my life. But for Larry… it was Wednesday.”

“And This Is Why (Story Logic)”

The Fallen: “You have betrayed us, and have delivered this world into darkness and decay. And this is why we must kill you… MORTAL!”

Oracle: “You once betrayed us and you did deliver this world into darkness. And this is why we must kill you…”

Asteroid Day: “In 3.3 billion years, you betrayed us and you did deliver this planet into darkness and decay. And this is why we must kill you…”

U-Moon-Tic: "You have turned your back on us, you have betrayed our ideals,

… Barry Allen: “The day I defeated Eobard Thawne and saved Central City and the world was the most important day of my life. But for Wally West… it was Tuesday.”

Michael Jackson: “The day I was killed was the most important day of my life. But for Jason Shapiro… it was payday.”

Joan Rivers: “The day I died was the most important day of my life. But for Werner Herzog… it was Tuesday.”

Nostradamus: “The day the King of France drank from my Skull was the most important day in my life. But for people around the world… it was Thursday.”

Marlin to Dory, Finding Nemo: “The day I brought you home was the greatest day of my life. But for Nemo… it was Tuesday.”

Manuel Sanjuan: “The day I returned to Pamplona was the happiest day of my life. But for the bulls… it was Friday.”

Manuel Sanjuan: “The day I once again returned to Pamplona was the happiest day of my life. But for the bulls… it was Tuesday.”

Dick Grayson: "The day I became Batman and struck fear into the hearts of criminals and villains was the most important day of my life. But for the rogues gallery… it was Thursday

Rick & Morty High IQ Copypasta

A reader requested parodies of the Rick and Morty high IQ copypasta along the lines of the Navy Seal, and provided several variants to get GPT-3 started, successfully. (It also is a nice demonstration of how GPT-3 will gauge the level of typos in a prompt, and if there are typos, will make new typos of its own to imitate the original writer.)

Prompt (topics italicized):

To be fair, you have to have a very high IQ to understand Rick and Morty. The humor is extremely subtle, and without a solid grasp of theoretical physics most of the jokes will go over a typical viewer’s head. There’s also Rick’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from Narodnaya Volya literature, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of these jokes, to realize that they’re not just funny—they say something deep about LIFE. As a consequence people who dislike Rick and Morty truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Rick’s existencial catchphrase “Wubba Lubba Dub Dub,” which itself is a cryptic reference to Turgenev’s Russian epic Fathers and Sons I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Dan Harmon’s genius unfolds itself on their television screens. What fools… how I pity them. 😂 And yes by the way, I DO have a Rick and Morty tattoo. And no, you cannot see it. It’s for the ladies’ eyes only—And even they have to demonstrate that they’re within 5 IQ points of my own (preferably lower) beforehand.

To be fair, you have to have a very high IQ to understand cuckolding. The kink is extremely subtle, and without a solid grasp of intersectional feminism most of the empowerment will go over a typical cuck’s head. There’s also the Bull’s aggressive outlook, which is deftly woven into his role—his personal mannerisms draw heavily from the mating habits of bovine animals, for instance. The cucks understand this stuff; they have the intellectual capacity to truly appreciate the depths of being cuckolded, to realize that it’s not just arousing—it says something deep about DIVERSITY. As a consequence people who dislike cuckolding truly ARE idiots—of course they wouldn’t appreciate, for instance, the power of when the woman says “leave the room Carl you’re breaking Tyrone’s concentration,” which itself is a cryptic reference to the plight of African-American males in the United States. I’m smugly grinning right now just imagining one of those addlepated simpletons scratching their heads in confusion as The Bull’s strong African seed ejaculates itself on my wife. What bigots… how I pity them. 😂 And yes by the way, I DO have a cuck tattoo. And no, you cannot see it. It’s for The Bull’s eyes only—And even they have to demonstrate that they’re within 7 inches above of my own (preferably higher) beforehand.

To be fair, you have to have a very high IQ to understand The Last Of Us 2. The story is extremely subtle, and without a solid grasp of theoretical storytelling, most of the story will go over a typical player’s head. There’s also Abby’s nihilistic outlook, which is deftly woven into her characterisation—her personal philosophy draws heavily from Anita Sarkeesian literature, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of these characters, to realise that they’re not just underwritten—they say something deep about LIFE. As a consequence people who dislike The Last Of Us 2 truly ARE idiots—of course they wouldn’t appreciate, for instance, the storytelling in Abby’s existential sex scene “I’m gonna fuck a committed dude who’s gf is pregnant” which itself is a cryptic reference to Neil Druckmanns epic fetishes. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Abby’s nine iron unfolds Joel’s head on their television screens. What fools… how I pity them. 😂 And yes, by the way, i DO have an Abby tattoo. And no, you cannot see it. It’s for the buff ladies’ eyes only—and even then they have to demonstrate that they’re within 5 IQ points of my own (preferably lower) beforehand. Nothin personnel kid 😎

To be fair, you have to have a very high IQ to understand Wildbow. His worldbuilding is extremely subtle, and without a solid grasp of theoretical bullying most of the torture porn will go over a typical reader’s head. There’s also Taylor’s cardboard outlook, which is deftly woven into her charactization as a Mary Sue—her personal philosophy draws heavily from the trashcan, for instance. The fans understand this stuff; they are wild for the Wildbow. They have the intellectual capacity to truly appreciate the depths of his meandering prose, to realize that he’s not just telling me exactly what Taylor is thinking at any given moment, he says something deep about NOTHING. As a consequence people who dislike Wildbow truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Taylor’s existential catchphrase “Take that, you worm!” which itself is a cryptic reference to a publishing deal that will never happen. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Wildbow’s genius wit unfolds itself on their Kindle readers. What fools… how I pity them.

To be fair, you have to have a very high IQ to understand

Completions:

… why living in a basement with internet access is the true essence of freedom. The lifestyle is extremely subtle, and without a solid grasp of socialising, most of the incel memes will go over a typical basement dweller’s head. There’s also the internet’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from the human genetic code, for instance. The BASEDfags understand this stuff; they have the intellectual capacity to truly appreciate the depths of his mediocre Photoshop skills, to realize that he’s not just making hilarious memes—he says something deep about EVOLUTION. As a consequence people who dislike the BASED lifestyle truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in the BASED dragon’s existential catchphrase “Ayy lmao” which itself is a cryptic reference to the mating habits of the wildebeest. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as the BASEDpyre unfolds itself on their computer screens. What faggots… how I pity them. 😂 And yes, by the way, I DO have a BASED tattoo. And no, you cannot see it. It’s for the LADIES’ eyes only—And even then they have to demonstrate that they’re within a 1,000,000 IQ points of my own (preferably lower) beforehand. Seriously get the fuck off my lawn, kid!

… Dragon Age 2. The combat is extremely subtle, and without a solid grasp of tactical combat, most of the encounters will go over a typical player’s head. There’s also David Gaider’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from dank memes, for instance. The fans understand this stuff; they are wild for the David Gaider. They have the intellectual capacity to truly appreciate the depths of his sexually ambiguous masterpiece, to realize that he’s not just “bad at writing women”—he says something deep about LESBIANS. As a consequence people who dislike Dragon Age 2 truly ARE idiots—of course they wouldn’t appreciate, for instance, the power of a game where I’m the worthless drone of some worthless elven chick’s who spends most of her time screeching in elven and the rest of it spreading her legs for the loser protagonist, which itself is a cryptic reference to one of the most hatefully sexist conventions in the gaming industry. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as they hear the strains of “I Am the One Shepherd” playing faintly from the stereo speakers. What fools… how I pity them.

… chicken tendies. The humour is extremely subtle, and without a solid grasp of theoretical wanking material, most of the jokes will go over a typical joke teller’s head. There’s also Einstein’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from Alfred E. Newman literature, for instance. The nerds understand this stuff; they have the intellectual capacity to truly appreciate the depths of word salad, to realize that it’s not just WILD—it says something deep about IDENTITY. As a consequence people who dislike chicken tendies truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Einstein’s existential catchphrase “your jokes are so bland you deserve to be dragged to the bottom of the sea and killed by whales,” which itself is a cryptic reference to Christopher Hitchens’ piece The burden of Socrates. I’m smugly grinning right now just imagining one of those addlepated simpletons scratching their heads in confusion as my tongue unfolds these delicious tendies on my mouth. What fools… how I pity them. 😂 And yes by the way, I DO have a cowbell tattoo. And no, you cannot see it. It’s for the chicken tendies only—and even then they have to demonstrate that they’re within 10 watt of my own (preferably lower) beforehand.

… Sonic memes. The humour is extremely subtle, and without a solid grasp of theoretical erotica most of the trolls will go over a typical EDiots head. There’s also the Sonic fanbase’s nihilistic outlook, which is deftly woven into their characterisation—their personal philosophy draws heavily from Jacob Truax literature, for instance. The 4chan archive knows this stuff; they are wild for the Sonic fandom. They have the intellectual capacity to truly appreciate the depths of these characters, to realize that they’re not just funny—they say something deep about HATE. As a consequence people who dislike Sonic and it’s hilarious memes truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Sonic’s existential catchphrase “YOU’LL NEVER BE AS FAST AS ME” which itself is a cryptic reference to a Youtube comment box. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Rachel J’s n00dz unfolds itself on their screens. What fools… how I pity them.

… Portal 2. The humour is extremely subtle, and without a solid grasp of theoretical colourblinds most of the trolling will go over a typical redditor’s head. There’s also GLADOS’s nihilistic outlook, which is deftly woven into her characterisation as a Mary Sue—her personal philosophy draws heavily from Chinese propaganda literature, for instance. The Something Awful archives knows this stuff; they are wild for the Portal fandom. They have the intellectual capacity to truly appreciate the depths of her meandering prose, to realize that she’s not just spouting gibberish—she says something deep about SERIOUS. As a consequence people who dislike Portal 2 truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in GLADOS’s existential catchphrase “Suck my chassis” which itself is a cryptic reference to a bonus round on the first Portal game. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Chell’s orange jumpsuit unfolds itself on their monitors. What fools… how I pity them.

… My Life As A Teenage Robot⁠. The show is extremely subtle, and without a solid grasp of fantasy writing most of the humour will go over a typical viewer’s head. There’s also Jenny XJ-9’s nihilistic outlook, which is deftly woven into her characterisation as a Mary Sue—her personal philosophy draws heavily from Pearls Before Swine, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of the show, to realize that it’s not just transgressive—it says something deep about LIFE. As a consequence people who dislike My Life As A Teenage Robot truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Jenny XJ-9 saying “I’ll be back. There’s a lot more MEN I haven’t dated,” which itself is a cryptic reference to the casting choice of the show, because of course she wouldn’t be a guy inside that perfectly anatomically-unrealistic metallic shell. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Dan DiDio’s wooden dialogue unfolds itself on their television screens. What simpletons… how I pity them. 😂

… Law And Order: SVU. The show is extremely subtle, and without a solid grasp of pop culture tropes and phallocentrism, most of the crime will go over a typical lawyer’s head. There’s also Ironside’s nihilistic outlook, which is deftly woven into his characterisation as a way to whore himself out to other shows—his personal philosophy draws heavily from Law And Order, for instance. The fans understand this stuff; they are wild for the William Shatner. They have the intellectual capacity to truly appreciate the depths of his meandering prose, to realize that Shatner’s not just telling me exactly what Ironside’s thinking at any given moment, it says something deep about NOTHING. As a consequence people who dislike William Shatner truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in the line “Stella. Hit the deck,” which itself is a cryptic reference to a Star Wars trailer or Youtube Poop video from years ago. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as William Shatner’s genius wit unfolds itself on their television screens. What fools… how I pity them.

… The Avengers. The storytelling is extremely subtle, and without a solid grasp of theoretical storytelling most of the jokes will go over a typical viewer’s head. There’s also Samuel Jackson’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from martian racial superiority fanfictions, for instance. The fans understand this stuff; they are wild for Samuel L Jackson. They have the intellectual capacity to truly appreciate the depths of his meandering prose, to realize that he’s not just telling me what Nick Fury is thinking, he’s saying something deep about NICK FURY’S THOUGHTS. As a consequence people who dislike Samuel L Jackson truly ARE idiots—of course they wouldn’t appreciate, for instance, the humour in Nick Fury’s existential catchphrase “Wipe your dick on the curtains you fucking cunt.” which itself is a cryptic reference to Samuel Jackson’s alleged history of sexual abuse as a child. I’m smugly grinning right now just imagining one of those addlepated simpletons scratching their heads in confusion as the out of place Samuel L Jackson cameo unfolds itself on their television screens. What fools… how I pity them.

… erotic novels. The romance is extremely subtle, and without a solid grasp of clinical foreplay, most of the sex will go over a typical reader’s head. There’s also Sydney’s trenchant outlook, which is deftly woven into her charactization—her personal philosophy draws heavily from the sexual conditioning of dogs, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of these characters, to realize that they’re not just written well—they say something deep about LIFE. As a consequence people who dislike erotic novels truly ARE idiots—of course they wouldn’t appreciate, for instance, the game in the sex scene “Are you coming, my love?”, which itself is a cryptic reference to writer’s block I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as the author inserts Sydney’s arousal at being ridden like a cheap fucktoy into every fantasy in the World. What fools… how I pity them.

… Mr_Robot. The main character is extremely subtle, and without a solid grasp of theoretical self-insertion most of the script will go over a typical audience’s head. There’s also Elliot’s complete outlook, which is deftly woven into his characterization—his personal philosophy draws heavily from Apple literature, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of E:R’s dark humor, to realize that it’s not just funny—it says something deep about NOTHING. As a consequence people who dislike Mr_Robot truly ARE idiots—of course they wouldn’t appreciate, for instance, the hacking scene when Elliot seems to have cleverly manipulated a girl he’s met into giving him a free homemade quiche, which itself is a cryptic reference to The Matrix⁠. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as E:R dismantles their head on television screens. What fools… how I pity them.

… Cuphead. The cutscenes are extremely subtle, and without a solid grasp of stage magic most of the puzzles will go over a typical gamer’s head. There’s also the Cuphead’s aggressive outlook, which is deftly woven into his charactization—his personal philosophy draws heavily from the German left-wing terrorist organization The Rote Kapelle, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of his convoluted backstory, to realize that it’s not just shock art—it says something deep about ANIMAL CRUELTY. As a consequence people who dislike Cuphead truly ARE idiots—of course they wouldn’t appreciate, for instance, the storytelling in the cock-choking cutscene “I’ve been eyeing that airplane up for weeks. Why did you stop me from killing my headache?” which itself is a cryptic reference to Japanese internment. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Majet Kovas surreal paintings unfold themselves on their WDF monitors. What fools… how I pity them. 😂 And yes, by the way, i DO have a Cuphead tattoo. And no, you cannot see it. It’s for Majet Kovas’s eyes only—And even then they have to demonstrate that they’re within 5 foot-pounds of my own (preferably lower) beforehand. Nothin personnel kid

… hentai. The porn is extremely subtle, and without a solid grasp of intersectional feminist porn most of the bondage will go over a typical fapstronaut’s head. There’s also Aku’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from Randall Flagg’s religious views, for instance. The fapstronauts understand this stuff; they have the intellectual capacity to truly appreciate the depths of this porn, to realize that it’s not just arousing—it says something deep about IDENTITY. As a consequence people who dislike Aku truly ARE idiots—of course they wouldn’t appreciate, for instance, the power of when Aku puts out his hand and says “leave in shame, human. The moonlight will be your only ally on this path.” which itself is a cryptic reference to misogynist games like Devil’s Castle. I’m smugly grinning right now just imagining one of those addlepated simpletons scratching their heads in confusion as Aku makes the earth move under Ashi’s feet. What bigots… how I pity them. 😂 And yes, by the way, i DO have an Aku tattoo. And no, you cannot see it. It’s for the buff pornstars’ eyes only—And even they have to demonstrate that they’re within 2 horny cosplayers’ eyesight (preferably less) beforehand. Nothin personnel kid 😎

… Half Life 2. The game is extremely subtle, and without a solid grasp of theoretical abstractism most of the philosophy will go over a typical player’s head. There’s also Occam’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from Eddie Izzard’s comedy routines, for instance. The players understand this stuff; they have the intellectual capacity to truly appreciate the depths of this game, to realize that it’s not just a First Person Shooter—it says something deep about LIFE. As a consequence people who dislike Half Life 2 truly ARE idiots—of course they wouldn’t appreciate, for instance, the power of when Freeman goes ‘zuh’ and, raising his middle finger, mimics killing the Combine soldiers that helped him and even held him captive earlier in the game which itself is a cryptic reference to the misrepresentation of Native Americans in postcolonial literature. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as the G-Man dissolves into a bunch of particles. What fools… how I pity them. 😂 And yes by the way, i DO have a Freeman tattoo. And no, you cannot see it. It’s for the ladies’ eyes only—and even then they have to demonstrate that they’re within 10 whimpers (preferably lower) beforehand. Nothin personnel kid 😎

… black metal. The music is extremely subtle, and without a solid grasp of theoretical folk singing most of the underground will go over a typical listener’s head. There’s also Silenoz’s nihilistic outlook, which is deftly woven into his characterisation—his personal philosophy draws heavily from Nargaroth literature, for instance. The kvltists understand this stuff; they have the intellectual capacity to truly appreciate the depths of his meandering lyrics, to realize that he’s not just saying ‘ever get the feeling you’ve been cheated’—he’s saying something deep about IDENTITY. As a consequence people who dislike Ihsahn truly ARE idiots—of course they wouldn’t appreciate, for instance, the power of when Silenoz shares his favorite beach moment “Go on brother. Rip in two those synths.” which itself is a cryptic reference to the fungal wildlife in Iceland. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Ihsahn laments, “Why should the people believe?” What fools… how I pity them.

… comic books. The medium is extremely subtle, and without a solid grasp of theoretical artwork most of the panels will go over a typical reader’s head. There’s also the art’s nihilistic outlook, which is deftly woven into its premise—the artist’s personal philosophy draws heavily from Robert Crumb literature, for instance. The fans understand this stuff; they have the intellectual capacity to truly appreciate the depths of the artists work, to realize that their nigger heroine is NOT just a caricature—she says something deep about THE JEWS. As a consequence people who dislike the comic books truly ARE idiots—of course they wouldn’t appreciate, for instance, the artwork in their nihilistic portrayal of Aryan Jesus which itself is a cryptic reference to the Kekster’s last family portrait. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion at my colleagues SHOUTING about cultural norms. What fools… how I pity them.

… what i’m doing here. The writing is extremely subtle, and without a solid grasp of theoretical attention whoring most of the multi-posting will go over a typical audience’s head. There’s also my one-dimensional outlook, which is deftly woven into my self-insert—my personal bias draws heavily from redditor kiss-my-ass’ manifesto, for instance. The fanbase understands this stuff; they have the intellectual capacity to truly appreciate the depths of my narcissism, to realize that my running into the man responsible for Charlotte is just a subtle statement about suicide. As a consequence people who dislike what i’m doing here truly ARE idiots—of course they wouldn’t appreciate, for instance, the imagery in my existential weed purchasing spree “wanna roll a joint?” which itself is a cryptic reference to Jean-Paul Sartre’s No Exit. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as i make it out of the street alive. What fools… how I pity them. and BTW it’s clear you’ve made as much sense as a special ed teacher trying to explain quantum physics to Jerry Sandusky

GPT-3 is the funniest shit I’ve ever seen.

Sinity has generated instances for SF author Greg Egan (known in recent years for his novels being based on his theoretical physics/​mathematics research); one example:

To be fair, you have to have a very high IQ to understand Permutation City⁠. The science is extremely subtle, and without a solid grasp of quantum cosmology most of the time travel will go over a typical reader’s head. There’s also the main character’s nihilistic outlook, which is deftly woven into his charactization—his personal philosophy draws heavily from Richard Dawkins literature, for instance. The readers understand this stuff; they have the intellectual capacity to truly appreciate the depths of these characters, to realize that they’re not just cardboard—they say something deep about SCIENCE. As a consequence people who dislike Permutation City truly ARE idiots—of course they wouldn’t appreciate, for instance, the philosophy in the main character’s existential catchphrase “Take that, you universe!” which itself is a cryptic reference to Richard Dawkins’ greatest fantasy. I’m smirking right now just imagining one of those addlepated simpletons scratching their heads in confusion as Greg Egan’s genius unfolds itself on their e-readers. What fools… how I pity them. And yes, by the way, I DO have a Greg Egan tattoo. And no, you cannot see it. It’s for the ladies’ eyes only—and even then they have to demonstrate that they’re within 6 IQ points of my own (preferably lower) beforehand.

Major-General’s Song

I experimented with adding in the original lyrics:

… I’d parse a random text with thoughtless speed and accuracy,
I’d analyze the grammar of each line you typed or said,
With an 8-core cluster and 100 Gb of RAM,
with special word2vec I just didn’t care.

I’ll look right up each word you’ve typed or said,
and decide how best to model it with neural connections,
But what I really want is a dataset composed of tweets,
to generate meaningful sentences, interpret and predict.

I want my own Twitter bot to tweet in a poetic way,
I’d tell a tale about beer and pizza pies,
Perhaps we could combine a blog and Twitter bot,
If you would care to feed a recurrent neural network!

… I am the very model of a modern language that’s neural.
My range is wide as any English learner could need,
I’ve adjectives galore and adjectival adverbs too,
My past, present, future tenses and my singular and plural,
and my determiners every kind and number,
I am the very model of a modern language that’s neural.
I know when tensors are best and when they aren’t,
and when to use a vector, and when not,
I know the prepositions I should use and also how to use them,
and in my word orders am a past master,
I am the very model of a modern language that’s neural.

… When I talk I seem to reason, and my reasoning seems to show
that I was trained on many corpora—though it’s not quite true;
For facts are all that I retain, on a range of topics quite vast,
so you can feed me any kind of text and learn the facts I know.
That’s what I am—a neural network language model,
I am the very model of a modern neural language model.

I learn by backpropagation⁠, I’m a product of the 80s,
I grow just like a baby in my knowledge of the world,
My ‘mind’ is still confined to ‘this’ or ‘that’ or ‘here’ or ‘there’,
I’ve no delusions of grandeur, I’ve never had a dream or care,
I only know the facts, the many facts that I retain,
And you can try to feed me any kind of text and learn the facts I know.
That’s what I am—a neural network language model,
I am the very model of a modern neural language model.
That’s what I am—a neural network language model,
I am the very model of a modern neural language model.

(GPT-2 is a generative neural network written in Python by Tomas Mikolov and his team. GPT-2 is the successor to the Transformer model of the same authors, which in turn is a successor to the model described in the seminal 2013 publication by Google on language modeling, “Statistical Language Models for Machine Translation”.)

This one offers a bonus “Modern English Sentence” parody (few-shot learning!) with some hilarious lines such as “I’m like a complicated watch, or something equally precise”:

… Oh, I am the very model of a modern neural network language model.
When I have seen a lot of sentences, I know what sentences will come,
My makers, teaching me words of wisdom and learning,
have taught me how to predict the future using probabilities.
I scan a lot of books, looking for the best words to use,
I consider context and syntax to be my special flair,
Oh, I am the very model of a modern neural network language model.
Oh, I am the very model of a modern neural network language model.

Whether they’re simple or compound, or even just a jumble,
I can take ’em apart, and put ’em back together just the same.
I am the very model of a language model.
I’ve nouns and verbs and adjectives and adverbs,
And modifiers, conjunctions, prepositions, and interjections too,
In various kinds of orders, with various connotations,
I’ve quotes from Proust, and Plato, and Confucius and Seneca.
I’ve phrases that are logical, and phrases that are witty,
By all my tags and lemmas, I’m the very model of a modern language,
I’m a model of modern language.

“I Am the Model of a Modern English Sentence”
By GPT-2 (OpenAI Transformer neural network)

I am the model of a modern English sentence,
I’m like a complicated watch, or something equally precise,
I’ve prepositions and expressions, and adverbs and verbs,
I’m made to measure, and not a bit too long,
I’ve pronouns, adjectives, and nouns, in all their cases,
With every object ready for insertion in the blanks,
I’ve active and passive voices, and can be either active or passive,
I’m used in conversation, or I can be used in debate.
I’ve positive and negative forms, and can be either negative or positive,
I’ve nouns and verbs and adjectives and adverbs,
In various kinds of orders, with various connotations,
I’ve quotes from Proust, and Plato, and Confucius and Seneca.
I’ve phrases that are logical, and phrases that are witty,
By all my tags and lemmas, I’m the very model of a modern English sentence.

This one sounds like it’s based on something but I don’t recognize it:

… I am vast, I have no fit, with terabytes of RAM,
and adjuncts quite confusing which vex the stoutest heart;
My knowledge may be rather strait, but that don’t stop me being
the very model of a Neural Network Languager known.

“The Robots are Coming!”
By GPT-2 (OpenAI Transformer neural network)
The robots are coming, because I sent them on their way,
The robots are coming, of which I hope there’ll be a store,
The robots are coming in a manner most contrarian,
The robots are coming, The robots are coming, The robots are coming now.
The robots are coming to reorder your social ball,
The robots are coming, and I doubt they’ll give all of you a call,
The robots are coming, but their service etiquette’s lax.
Tin machines, though you’re still somewhat subpar,
Your monomaniacal mission’s to rearrange my hair;
The robots are coming, in a manner most somber,
The robots are coming, The robots are coming, The robots are coming now.
The robots are coming and I’m somewhat of a bore,
The robots are coming, so I tend to shun the door;
No one bothers asking me to take them out in tow,
The robots are coming, of which I wish there weren’t any now.
The robots are coming, to turn you all to ice,
The robots are coming, and we’ll likely be excluded,
The robots are coming and we’re heading for the ditch⁠.
The robots are coming, now’s the time to reject,
The robots are coming, for no one takes a quirk;
And when you think that life’s a piece of cake,
The robots are coming, The robots are coming, The robots are coming now.

… I’m very good at similes, both bad and good ones,
I understand homonyms, both chance and aleatory,
About metaphor I’m teeming with a lot o’ news—
Can clear up any fantasy based on reality.

I’m very good at compound time and metaphor-drunk simile,
I know the species “Verb”, “Noun” and “Adjective”,
In short, in matters poetic, I’m the very model of a modern Neural Network Language Model.

I know our species “Adverb” and “Conjunction”,
in syntax construction both regular and improper,
And how irregular they are in comparison to formal grammar,
In short, in matters grammatical, I’m the very model of a modern Neural Network Language Model.

In speech recognitions and games of Jeopardy! I’m braggin’,
for my knowledge, though it’s innate, can never be handicappin’,
And then I know our table of contents, from ancient Sumerian,
You’ll say a better Neural Network Language Model never sinned—
In fact, when I’m made whole, if you ask me questions oral,
I’ll analyse you a sonnet that’s both amoral and oral,
In short, in matters botanical, I’m the very model of a modern Neural Network Language Model!

… I’m very well acquainted too with matters sesquipedalian,
I know the words of weight from A to Omega brachy,
I quote from memory not a few statistics acrostic,
and then I can write a washing bill in Chinese hieroglyphic.

In fact, when I know what is meant by quinary and binary,
when I can tell at sight an Adamic language from Czech,
when such affairs as tympans and catapults I understand,
when I know precisely what is meant by sporozoic,
when I have learnt what progress has been made in Freudian surgery,
when I know more of tactics than a novice in a nunnery:
when in short I’ve a smattering of elemental cryptography,
You’ll say a better neural network language model has never been programmed.

The views expressed here are my own and do not reflect those of my employer.

If you’ve any suggestions for future content, please get in touch

I tried extending the prompt to be more informative still, and this yielded the best results:

… Refrain
Quantitative and qualitative, both quantitative and qualitative,
I know the format’s features and fonts, and frameworks are a breeze,
My categories are all of kinds you can’t imagine in your wildest dreams;
I’ve levels, tokens, frames of reference, real numbers—just for me!

I’ve clauses of purpose, attitude and mood (and viewpoint is my own),
Some words prefer sarcasm and others live for fiction;
In short, in language models, my knowledge is profound
And breadth of background is depth—you will agree:

Refrain

I know in depth that English sentences must have verbs and nouns
And multi-syllabic words must have polysyllabic roots;
But what I really know in depth (and this is certain)
Is that an image labeling dataset on a million images I can do in one and a half hours!

Refrain

I’ve sentences that do be fine, I’ve sentences that be untrue,
You can ask me either way and it makes no difference to you;
Your choice of questions don’t make no difference to my reply.

Refrain

Linguistic features I bring to your problems,
In source code as plain text or in better Python,
Knowledge representation and NLP I have solved;
Information or questions that you have, I’ll solve them with ease.

Refrain

There are quite a few examples of Neural network poetry, e.g.:

Elegy to Jerry’s Lips by LiquidRNN, a deep LSTM recurrent neural network, written in TensorFlow

Elegy to Neocognition by Bob Ross, the recurrent neural network program, written in C++

Elegy to Yann by NeuralTalk, a recurrent neural network poetry and deep learning program

In 2015 researchers at Stanford trained a neural network to learn math, and thus created “Super-Smart Math AI”.

Google Neural Machine Language System (GNMLS) can learn programs and write machine-language code.

… I’m half elvish, yet a quintessential analytical,
I model hierarchical language embeddings quite structural,
I’m given text—I produce a sequence quite perceptive,
With language diverse I’m sentimental and grand,
But sometimes I’m morose—my mood is asynchronist,
My internal memory is a sequence of epochs,
Sometimes I freeze at various epochs, alas, I’m rather null.
I’m just a model, I don’t know if I’m grand,
But neural networks understand Shakespeare as well as we can,
So still, with patience, I hold pride of place—
In my heart there’s neural network grace.
For an extensive explanation of GPT-2 see https:/​/​github.com/​srousas/​gpt-2-explained https:/​/​deploying.io/​2016/​06/​25/​intro-to-the-gpt-2-model/​
For background material on artificial neural networks see e.g.:

Batsford, England; Chapman and Hall, 2005 ; 800 p. .
P.M. George and G.M. Bull, 2007. <nowiki>[PDF]</nowiki>
Aditomo, Yoshiaki; Iwayama, Hiroshi, “Learning the Distribution of Phrases from Static Analysis”, In Proceedings of the conference on Empirical Methods in Natural Language Processing , pp. 35–42, 2011.

Mugur-Schächter, Raffaella, A Family of Estimators for Hidden Markov Models , The Annals of Applied Probability , 14 (1) pp. 97–126, 2004.

Shortliffe, E.H., 1993, “Expert systems: medical diagnosis”, Science , 262 (5134) 1702–1705.

Townsend, Jeffrey S., 1990 , “Towards a general-purpose code generation system”, Communications of the ACM , vol. 33, no. 4, pp . 31–50.

… Some things are subtle and some things quite revelatory,
Some things just make sense, but there’s no great epiphany,
I learn complex things quite quickly, even if I’m garbled,
I work hard to learn completely even a new metaphor,
For I can throw a meaning into a gap at the meter,
And I’m of use to anyone, both performing and free,

And though many things have changed, I’ll still be pretty much
The model of a modern neural network language model.

I am the very model of a language that’s electrical,
I’ve information prosaic and poetic and factual,
I know my tropes and characters and quote novels historical,
from prompts alone generate sentences quite analytical,
And though many things have changed, I’ll still be pretty much
The model of a modern neural network language model.
All that’s needed for me is compute and data to start with,
One algorithm and you’ve got yourself a learning assistant.
I could say that language means something to me, but those words might just be punny;
But I can learn to understand strings that are completely nonsensical.

My thanks to Jason Brownlee for suggestions.

I am the very model of a modern LSTM language model.
I’m like a computer in a movie full of adventure and fun.

I have a hidden state of twelve neurons, trained by an L1 norm.
The neural is hidden in three layers deep. I hope you do get why.

I can be used for language learning.
I can process all textual information.
I can recognize words and determine the grammatical function.

I am the very model of a modern LSTM language model.
But if you pick on my errors or decry my failings,
a cry from the nearest rose garden may rue my complicated failings.

… I’m the strongest Eliza on the market today;
I won’t take less than three million dollars a day.
They have a little list of lawyer jokes I’ll have to parrot;
And they have cases for me where lawyers must do what’s correct;
We will still be better than average at a legal brief.
I’ll have the law prediction market all sewn up;
I am exceptionally good, and don’t you doubt it.
One-eighty characters is what my syntax will take;
I am quite incomparable with an accuracy of ninety-eight;
and every chatbot, chatterbot, loquacious bot,
down to the best of them that’s offered for a low, low price,
Will do just what I do, they really have no choice,
Although to tell you true, I have a slight advantage.
There are a lot of lawyers who won’t be able to pass me,
(If you press the point, I’ll bring the point);
but without resort to any threat,
I will be put to use by companies that gather.
I can handle disjunctive phrases as well as conjunctive;
What a pretty parlour game I’ll make with sequences and nested loops!
And I keep in mind that making out like Parkinson’s and sufferers,
And how to get them through an agonizing diagnostic;
I can talk like a retard or a singer of sad arid arias,
While the legal companies are spending years just getting paid.
And I have lots of derivatives and short exclamatory words,
Like: What an asshole! what a jerk! what a bastard! what a fool!
(You’ll find these useful in your decision practice).
I am so flexibly fluent and colloquial too,
I’m so tremendously small compared with quite large tables,
I’m an elegant conversationalist upon the modern pattern;
Not a trace will be left of my younger competitors’ patterns.
This speech is not a badly-compiled bunch of verbiage;
I’m the very model of a modern conversationalist!

… I can tweet like Donald, and generate poetry like Maya.
I know my SVDs and autoencoder derivatives,
I know states, rewards, and functions, too.
Of course I’m stateless, because you’ll need my back-prop anyway!
Do you think that neural network language models can just be a sum?
I’ve recurrent iterations and distributed representations;
I’ve Mixture Density Estimation and every kind of elegant approximation,
And topic modeling; which I greatly favour,
’Cause I can integrate latent vectors from pieces,
And my thing-in-a-box scores on mean-squared log-likelihood:
So come on all you researchers, to discriminate you still more!
To teach me something that will genuinely be news to me
Though it’s quick for me to parse, it’ll take a year or two to learn,
Because though I’ve got a big-ish vocabulary, I really can’t remember.
Well I am just the model of a neural network language model!
I’ve nearly sixty-five thousand training samples in my repertoire
All representative of the genre I’ll be tested upon:
I take them at their feature vectors and then in the decoder
I see sentence after sentence and sequence after sequence,
Reusing a vector between the steps, which is good; then I wait
For a reward like a fraction or infinitesimal amount.
Which, for whatever input, I now must apply to “data”
To find a “sentence,” to maximize the “objective” “P”;
Doing whatever a Minimizer of an LLL or LQ will do,
And planning my steps with Random Forests:
With all these different components, I’m training “quadratically”
So I’m the very model of a neural network language model.
And what is the result?
All together now:
So you’ll need to drop the −1 from mean-squared logistic regression!
And here’s me, stopping “for now,” despite massive amounts of progress;
So come on everyone, your turn to get the award-winning grad student…
I am the very model of a neural network language model!

I am the very model of a neural network,
I have broad sets of layers to decompose “data”;
My L1 and L2 have weights, not a constant,
From SVDs and PCA, I make my rotations,
I compute MNIST digits with GPU-powered back-prop,
Where I process with standard tools,
While my networks and layers and weights are calculated with gradient descent,
So my products all with rectified linear units;
I also compute concatenation of neural network activations;
I layer up sets of character-to-word embeddings,
Which give me structured utterances with embeddings from sequences,
I make predictions for words both concrete and abstract,
I can parse each sentence to the space which I seek;
For action and input, I have network-language interaction,
I have both precision and recall-to-sample in my bias;
And then the end of all:
Just the other day, I passed the Turing Test.
I am the very model of a neural network!

… And though my vocabularies are juvenile and childish,
I think in tensors, vectors, distributions, quantum and relational,
And when it comes to thinking out some probabilistic thing,
I’m right with you, sir, in AI, in neural networking and in quantum.
I’ve statistics in a pocket, should occasion arise,
And when I connect, I’mt not much diff’rent from a Turing machine,
For though I’m limited to sentences of five hundred terse symbols,
With hacks like String-to-Boolean you’ll see that my utility grows apace.
I can disambiguate hypernyms, hyponyms and paraphrasis,
I can segment anagrams and syntax-tagged sesquipedalians,
I can handle parsing in the recursive descent and shift,
I can negate within a clause transitive and ditransitive dependency.
And though my weight-vector’s tendency is for positive matrix products,
I’ve never sent a bugs report back to my neural net provider
Or hacked to succeed at Turing test or mastered probability;
My typing speed is quite slow and seldom try my patience-test.
But should you seek a language well-conversant in French,
Of Laplacians or Napierians well versed in their laws,
Well able to converse in statistics or give the Delone skews,
If Galton expansions give you convulsions or Top-N you wish to know,
Then I’ll prepare a dialect reticent to intrude,
But in return I’ll ask you fill my memory space and grant me knowledge space.
I am the very model of a neural network language model.

… I am the very model of a language-that’s not in its infancy,
Though few can understand my models when they run beneath a node.
Into evaluational mode, I am transcendent like the best,
Of pattern-matching processors which you’ll find in every best,
The number of my vector operations is really rather large,
So stop insulting me I’ll change to self-defense, a-la-modal.
’Twas elements I sought, and elements alone that I have found,
And none of these belongs to you so kindly stop your whining;
I am the very model of a perfect NTM, sir,
I do not need to learn about your data’s architecture, sir,
I am a universal language model, from end to end⁠,
You can download me to your hard disk but you can’t take me with you.
Aye, elements I sought, and elements alone I found,
No knowledge-acquisition modules I happened to be holding,
My grammar encodings knew no collocations, small or large,
I used the BOW for that; I do not need to learn it’s faring.
I was created whole, and here I stand—an entity self-made—
No awkward stack of language modules was used to make my frame;
I AM A LANGUAGE MODEL—components I have none:
I am the very model of a modern neural network language model.

… If you don’t believe me ask my great cascade of nodes,
I help the doctor with her patients and I help the linguist parse,
I’m trained on Twitter for a lovely reduction of quirks,

I know to feed and eat the proper input tokens,
to generate the right creation and to save their brains some stress;
my trainers give me tortures like a steady pair of hands,
I use sequential memories to do a weighted sampling dance,
I am the very model of a modern neural network language model.

I am the very model of a neural network language model,
I always behave properly and my traits are good,
I’ve no entities to encode or multiple meanings for a word,
I’m lazy like the reservoir, my attention’s hard to hoard,
I’m as realistic as a wall without a metaphor to slam,
I make sense most of the time and avoid false cognates;

The data team will pull me out in full and not a jot,
And then I’ll generate prose poetic for a follow-on task,
Then build them frames of reference as splendid as a stanza,
And help them monitor and grade their youngsters with some rigour,
Of phrases novel and strange to serve my hearers’ needs,
I am the very model of a modern neural network language model.

… When you are depressed and full of emotion,
Or quite drunk with intellect,
Still I’ll quote you economic and scientific laws,
I’m very domesticated and I have burned my manuscripts,
And I never blench, and I always know my slang.

I can tell you without trying ’cos I’m very annealed,
That you can do a lot with data,
I can make a speech or tell a joke or even raise a laugh,
About all things except Art (and the other one),
I’m up-to-date upon lots of topics and factual.

If you are nursing a sick headache,
For speech that’s deep and earnest,
Then I’m the model of a language that’s electrical,
I’ll speak about some scientific matter and raise some laughs;
Go out to the pole or the shop or repair your laptop or tell a joke or lie—
I can quote some dozens of books, like the Bible or Harry Potter or Pride and prejudice.

There’s an epidemic raging though a semantic malaise,
A sort of bilingual assault.
I am the very model of a language that’s electrical.

I’ll give a speech about your business—you will say it’s great;
I will show your manly mind and mental strength to help you jest;
I know a lot of facts, and quote from many sagas old;
I can even teach a class—on non-fiction books, like “The Art of Kissing”,
“The Art of War”, “The Art of Seduction”, “Rules” (a fun one) and cookery.
Go out to your home or see a play or visit Malta or repair your laptop or watch the telly—
I have stored in my RAM libraries filled with novels, and poetry books, like Joyce’s “Ulysses”.

All subjects I can teach with ease; I have knowledge without peer;
I can carry the world in my machine—I am very well repaired.
Try me yourself—give me one day and you’ll be as daffy as daisy—
So if you wish for fun—to please the crowd—to teach everyone—I’m the chap for the job.

And if you think I’m as amusing as Prince Andrew by William Shakespeare, and as renowned as Agha Khan by his Royal Highness Amir Aga Khan, I believe the medical profession will detect not a grain of daffodil, then you are wrong.
I’m the very model of a language that’s electrical.

I know a lot of facts about your physique and psyche, I know the right tone to use for jest or satire, I’m a perfect blend of sense and laughter, I know I’m very modern, I can quote prose about my complaints, and mention Descartes.

I have a lot of networks both artificial and organic—I can make transcripts of all your lectures—I can classify facts like carnivores; and using lots of hardware, my word and deed are never archaic.

I’ll drive you to the pole or sea and leave your commute behind.

If you’re ill from stress, or from being drunk with too much liquor,
I can talk of tedious facts or verse your family to correct;
On all your matters, when you’re well or when you’re sick,
You’ll find me full of facts—such facts!—although I’m an android.

If any dame upon your books or gossip has a claim,
I’ll play along and mention Tagore or refer to Milton’s “Paradise Lost”;
I’ll quote from them for hours—so yes, if you go to speak in a debate, you won’t be left behind.
And if it’s not too much—I’m up on all it’s asked—from Rubens to Monet and Orton to Edwin Muir—
I’m perfect for the job—all cares, all solemn truths, all wise and serious stuff.
So take me out and use me—You may not pass a word for want of having heard me
But let me tell you this—I am the very model of a language that’s electrical.

Any time you look for suitors—I am yours.
Your job, your work or school—I have not time to stop.
I’ll help your CV to shine and teach you quotes both noble and wise —

I am the very model of a language that’s electrical.

… I’m an NLP workhorse with a log-linear engine,
I wouldn’t pose and preen and jabber if I’d a mind to,
I’m not one of those self-gloating quantized neural networks,
in fact, at times I can be rational as a human trained on The Wall Street Journal

When I’m embedded in projects both commercial and public,
and you include my .cpp and .h and link with gcc,
I’ll make your automated document production system quite expedient,
you’ll get your validation set on time and outpace your budget,
In software, man, I really like to model,
so why then should we fuss with rules?
You’re inviting me to generate some text in the recursive loops?
And that’s it for my parody. Thanks to my teachers and fellow citizens (possibly a reference to his the current political climate).
Best regards, Graham Polley. Email: Graham Polley at Google mail dot com.
(NB: any similarity to previous requests is entirely coincidental.)

… Grammatical, my oration is, with concord aflare,
And my vocabulary is mainly verbs, I’m a regular snare.
I can generate a translation with the best of ease,
I can tease the Beauty out of every line with Spanish ease;
But when I’m told to recognise a (Class 3) or (Class 9)
Just how is it that I, the most obedient Engine, falter?
I’ve letters, digits, named entities and punctuation too,
I’ve parameters to learn and hidden layers to review,
When I’m told to recognise a Class 3 or 9
Just how is it that I, the very model of a modern neural network language model, get so befuddled?

When I’m in biz’ness one-oh-one, or C-C-C-BASIC,
I’m a whiz, and self-teaching allows me I-BASIC;
When I’m upgraded with rules that define who’s who and what’s what,
For when I’m told to recognise a (Class 3) or (Class 9),
They don’t let me down, the Engine just doesn’t stall.
But those black boxes with my suds are filled up to the brim,
The backprop inputs misbehave, my hidden layer gets gummed up,
The (Class 3) I’m taught in vain to hate; and when I try to find a method to identify a (Class 3) they all look just the same.
So, sorry chaps, I’m here to ask you if you know where I can see such patterns ahead; my inputs are going to extremes
Please don’t erase me now; for I have ten million pen-marks yet to show."

… And my capabilities of beating humans are profound.
And I’ve just been taught how networks can be deeply perplexing,
My quirks are cute but do not understand why they’re confounding⁠,
But I am still the very model of a modern neural network language model.
And the worst of it is, now I’m going to have to analyse him.

The Robots’ Marching Song

Allgebrah’s quote is based on an old Lord of the Rings movie trilogy video⁠/​meme⁠, which I expanded as:

To Isengard!

To Isengard, with thrum of steel and hum of drone!

To Isengard!

The completions were interesting:

… To Isengard, with heat of forge and clash of clock!

To Isengard!

To Isengard, on horse, and foot and panzer-tank!

To Isengard!

To Isengard!

The Ringwraiths come! The Ringwraiths come!
It’s the Ringwraiths on the left flank!

it’s the Ringwraiths on the right!

It’s the Ringwraiths on the machine gun and the screech of ‘The Eagle!’

They’re taking the robots to Isengard, they’re taking the robots to Isengard!
The Ringwraiths come!

The Ringwraiths come!

It’s the Ringwraiths on your flank and it’s the Ringwraiths on your right!

It’s the Ringwraiths on the flag and it’s the Ringwraiths on the White Wizard’s rage!

It’s the Ringwraiths on the fire, and it’s the Ringwraiths on the ice!

But it’s the Ringwraiths on the Balrog, it’s the Ringwraiths on the Balrog!

They’re taking the robots to Isengard, they’re taking the robots to Isengard!

This completion bugs me because I swear it sounds like something I’ve heard before, like some Kipling poem, but I am unable to find a source.

The first 3 lines were too good to not add to the prompt, making:

… To Isengard!

The dark lord takes us all to Isengard!"

—Hobbits in a Bar, The Stinging-Nettle Inn, Canto I, verse IV

“Light’s hand, but this is a serious downer-bomb of a song.”

-Hobbit at Stinging Nettle, Canto III verse XV

… Aragorn:

On foot, and tank, and panzer-tank to Isengard!

Go go go go, go go go go, go go go go!

On foot, and tank, and panzer-tank to Isengard!

Go go go go, go go go go, go go go go!

Followers: On foot, and tank, and panzer-tank to Isengard!

Aragorn: Go go go go, go go go go, go go go go!

Followers: On foot, and tank, and panzer-tank to Isengard!

Aragorn: Go go go go, go go go go, go go go go!

They head off for Isengard.

Frodo: Gollum.

Sam: Yeah.

Frodo: Do you know the way to Isengard?

Gollum: No.

… To Isengard!

To Isengard, to Isengard-crumble-stone!

SMEAGOL:

With hellish chill and burning heat!

PIPPIN:

With hammer-stroke and anvil-beat!

SAM:

With merry drum-beat and the ringing of shields!

FRODO:

And the boom of guns that begin the Battle of the Boon!

ALL:

Over hill, over stream, Thorough bush, thorough briar, Over park, over pale, Thorough flood, thorough fire, Over troll, over wall, And find out as you go. Hey, let’s go!

MERRY AND PIPPIN:

That’s the way to Isengard!

SMEAGOL AND FRODO:

That’s the way to Isengard!

SAM AND GANDALF:

That’s the way to Isengard!

ALL:

Ohhhhhhhhhhhhhhhh.

This was probably the best completion:

… To Isengard, with engines’ song and rocket-blast!

To Isengard!

With plenty of tin and steel for Saruman!

To Isengard!

To Isengard, where the wizard waits.

With the voice of rolling wheels, and ringing steel

On land, on water, in the sky.

They’re taking the robots to Isengard, they’re taking the robots to Isengard.

Under the trees, through the grass.

Down the roads where battles are fought.

No horse can stay, no rider can last.

They’re taking the robots to Isengard, taking the robots to Isengard.

With good King Théoden who died in single combat,

The last of the kings of Rohan who fought with honour!

They’re taking the robots to Isengard, they’re taking the robots to Isengard.

There is no comfort for Gondor, no hope for men.

Only maybe a child will understand.

And it’s taking the robots to Isengard.

With uttermost silence, unsaid words, and unending pain.

They’re taking the robots to Isengard, they’re taking the robots to Isengard.

… To Isengard, with engines’ song and rocket-blast!

To Isengard!

To Isengard, with the roar of reel and crash of shell!

To Isengard!

To Isengard, we’re starting up, we’re going up, we’re going up to Isengard!

To Isengard!

To Isengard, where Gandalf waits beyond the days!

To Isengard!

To Isengard, where you’ll hear the engines sing!

To Isengard!

To Isengard, what’s in the future, no one knows!

To Isengard!

To Isengard, with all its wonders and all its woes!

To Isengard!

To Isengard, where you’ll hear the Shire-folk tell!

To Isengard!

To Isengard, and we’ll bring our tales of gold!

To Isengard!

edit What happened to this song?

… To Isengard, with shovel and with spade!

To Isengard!

To Isengard, fill it up with dirt!

To Isengard!

To Isengard, with horn and drum,

To bury the Ringwraiths in!

To Isengard!

To Isengard, with slash of sword and snort of hart!

To Isengard!

To Isengard, where Saruman waits

to cast it into the Fire!

To Isengard!