Awww, ChatGPT is being all heart-warming and life-affirming again! This time, I asked it to create illustrations in the style of a stained glass windoAwww, ChatGPT is being all heart-warming and life-affirming again! This time, I asked it to create illustrations in the style of a stained glass window and I thought it did quite a nice job.
Awww! ChatGPT has written another heart-warming little story... I'd only meant to test some code I'd recently added to C-LARA, but then felt the resulAwww! ChatGPT has written another heart-warming little story... I'd only meant to test some code I'd recently added to C-LARA, but then felt the result needed to be preserved for posterity. Why can't we all be as nice as this AI?...more
[image] [image] That moral little AI is at it again. Learn how to save the planet and use conditional constructions! Full text here.[image] [image] That moral little AI is at it again. Learn how to save the planet and use conditional constructions! Full text here....more
A bridge player friend recently married an Icelander and is trying to learn her husband's language. I showed her C-LARA and asked if she would [image]
A bridge player friend recently married an Icelander and is trying to learn her husband's language. I showed her C-LARA and asked if she would like it to write her a easy picture book story to practice with. After a little discussion, we agreed that a dragon would fall in love with a queen who played bridge and have to learn the Acol system to win her heart.
It turned out that GPT-4o's Icelandic is still rather uncertain, but our Icelandic colleague Sölvi helped clean it up. You can see the result here. _______________
In Anna Drottning og Drekinn Dóri: Jötnarnir koma, a group of frost giants turn up, and the only way to save the kingdom is to defeat them at the bridge table. Here, Queen Anna (possibly distracting the giants with her opulent cleavage, though the text is unclear on this point), plunks down the winning card to bring their nefarious schemes to naught.
I asked C-LARA for a pedagogical picture book designed to appeal to 14-year old male students of English and entitled "Supermodel Lisa Loves Ph[image]
I asked C-LARA for a pedagogical picture book designed to appeal to 14-year old male students of English and entitled "Supermodel Lisa Loves Phrasal Verbs". Full text here.
It seems to me that the AI has a reasonable understanding of what 14-year-old boys find interesting (view spoiler)[Hint: not phrasal verbs (hide spoiler)]. Apologies to female readers who wander in and find they are unable to retain their breakfasts. You have been warned....more
We noticed that our kitten Finley refused to eat pork. I asked C-LARA for a picture book suitable for 8-12 year olds and highly respectful towa[image]
We noticed that our kitten Finley refused to eat pork. I asked C-LARA for a picture book suitable for 8-12 year olds and highly respectful towards the Muslim world about a kitten who converts to Islam. Full text here.
Not would like people to know that the character of Lily isn't based on her....more
I am having so much fun with the new C-LARA picture book functionality, which lets you create a multimodal picture book in less than an hour! This repI am having so much fun with the new C-LARA picture book functionality, which lets you create a multimodal picture book in less than an hour! This report, which I've just posted here, shows you how to do it, using the fully AI-generated example text Kitten's Busy Morning.
People who already know English, French, German and Latin should only need a few days to learn the basics of Esperanto, and it's so much fun! Last weePeople who already know English, French, German and Latin should only need a few days to learn the basics of Esperanto, and it's so much fun! Last week, I read Teach Yourself Esperanto; when I'd finished, I looked around for the Esperanto edition of Le petit prince, which you'll find here. If, like me, you are a fan of this book, you'll find it very easy to read as soon as you've mastered Esperanto's extraordinarily ingenious system of prefixes and suffixes.
Here, let me show you with one of the King's little speeches. I'll first give you the Esperanto as it's presented in the book, then broken down into units, then glossed in English, and then translated:
"Se mi ordonus al iu generalo aliformiĝi en marbirdon kaj se tiu generalo ne obeus, la kulpo ne estus lia," li kutumis diri, "la kulpo estus mia."
"Se mi ordon-us al iu general-o ali-form-iĝ-i en mar-bird-o-n kaj se tiu generalo ne obe-us, la kulp-o ne est-us li-a," li kutum-is dir-i, "la kulp-o est-us mi-a."
"If I order-HYPOTHETICAL to some general-NOUN other-form-make-INFINITIVE sea-bird-NOUN-ACCUSATIVE and if that general-NOUN not obey-HYPOTHETICAL, the fault-NOUN not be-HYPOTHETICAL he-ADJECTIVE," he custom-PAST say-INFINITIVE, "the fault-NOUN be-HYPOTHETICAL I-ADJECTIVE."
If I ordered a general to turn into a sea-bird, and the general did not obey, the fault would not be his," he had the habit of saying, "the fault would be mine."
See what I mean? ______________
I have been talking with ChatGPT-4o, who turns out to be quite good at Esperanto, and we have put together a C-LARA version of the first chapter, here. The text is divided into component morphemes as in the example above. Try hovering over/clicking on things, and you'll soon appreciate what an ingenious language it is! I particularly liked the following:
We are working on developing better ways for the AI to annotate Esperanto - I had to do a fair amount of cleaning up here. Hopefully more about that soon......more
What a lovely idea! An alphabet book where you have the usual alphabet book animals, but they're all assigned to different letters... because, for exaWhat a lovely idea! An alphabet book where you have the usual alphabet book animals, but they're all assigned to different letters... because, for example, in Portuguese the word for bee, abelha, actually does start with a A! If you want your bright seven year old to become a linguist, you could definitely find a worse starting point.
If you were wondering why I've been posting so little the last few weeks, then wonder no more. Available for free download here. ___________
But seriousIf you were wondering why I've been posting so little the last few weeks, then wonder no more. Available for free download here. ___________
But seriously...
ChatGPT-based Learning And Reading Assistant (C-LARA) is a project that's been taking up most of my time for the last year. The basic idea was to build a web platform that lets people create easy-to-read multimodal texts in foreign languages, and have ChatGPT-4 do as much of the work as possible. Chat appears in two roles. With its software component hat on, it writes the texts, cuts them up into roughly sentence-length pieces, adds glosses to the words, marks them with root forms, and adds TTS audio. With its software engineer hat on, it's written most of the codebase. This report gives you a detailed picture of what we've done.
You may think there are too many details - does it really need to be 144 pages long? But it hasn't primarily been written for you, it's been written for ChatGPT-4. Although the AI is responsible for the greater part of the work performed in the project, it periodically has to be reinitialised, and then I need to tell it who it is again. Having this report available makes the job easy: I can give it the text in half a dozen instalments, which takes a quarter of an hour, and then it's up to speed again.
For humans, here are some of the bits you might find interesting. First of all, we've made C-LARA easier to use. There's a new top level called "Simple C-LARA", which lets you create a multimodal text with an initial request and a couple of button presses. You choose the text language and the glossing language, provide a sentence or two telling the AI what to write, and it creates a short illustrated text for you. (The illustrations comes from DALL-E-3). There are straightforward options to edit and correct when it gets things wrong. You can also paste in an existing piece of text if you prefer, and tell the AI to annotate it instead. For example, that's how I created the multimodal Norwegian passage in my review of Jon Fosse's Melancholia I-II.
Second, we've done some work to evaluate C-LARA. We describe an experiment we presented at the ALTA 2023 conference late last yeat, where we created six texts of widely different kinds in English, Faroese, Farsi, Mandarin and Russian and carefully checked how often the AI was making mistakes as it wrote and annotated them. Not surprisingly, it's much better at some languages than others. It turns out to be nearly as good at Mandarin as it is at English, but it's clearly worse at Russian, worse again at Farsi, and having serious problems with Faroese. Of course, it's miraculous that it can do anything in Faroese, an obscure Scandinavian language spoken by about 50,000 people. We repeated the experiments a few months later, and found it had improved a good deal in English. We also analyse the codebase to quantify the AI's contribution to writing it. We found that it had written nearly all of the simple modules and done the greater part of the work on the middling difficult ones. There were a couple of top-level pieces of functionality, in particular "Simple C-LARA", where it couldn't deliver: they required an overview of the whole project, and its context window doesn't seem to be up to it yet. I'm curious to find out what happens in GPT-5.
Third, we present some case studies where people have started to use C-LARA. We have a primary school teacher in Holland who teaches a weekly class for Romanian kids whose parents don't want them to forget their heritage language. We'd never used C-LARA with Romanian, a language I know nothing about, but Lucretia just tried giving it requests in Dutch and said it produces cute, funny little Romanian stories that the kids like. We've also been collaborating with linguists at the University of New Caledonia, who are using it for a couple of the Indigenous languages there. Here, the AI can't help with the writing; they need to create the texts by hand, but that's possible too. They're pleased with the results, which are freely available on the web.
In the appendices we give more details, including examples with step-by-step screenshots showing how to create a C-LARA text. Try it out, the platform is already a whole lot of fun to play with! It's just amazing what you can do with an AI to help you. ___________ [Update, Apr 9 2024]
One of the most useful things about writing this kind of document is that it forces you to think carefully about what tasks you should be planning to do next. We put together a long list in the "Further work" section (§9.1), and we've already started. More about that in a recent post on the C-LARA blog....more
Inspired by Mots d'Heures: Gousses, Rames, ChatGPT-4 and I have been discussing this apparently innocent nursery rhyme. We can hardly believe our Inspired by Mots d'Heures: Gousses, Rames, ChatGPT-4 and I have been discussing this apparently innocent nursery rhyme. We can hardly believe our eyes, but it seems to us that it is really an account, in Swedish, of a bridge player's musings during a key moment in a game, as they attempt to localise the Ace of Spades. Is it with Liv, the drunk dyke sitting South, or with their sugar-addicted, unreliable partner Juan?
Or what do you think? Read our compelling analysis and judge for yourself:
Barbar, bläckskit! Here, the player's frustration with the elusive Ace of Spades (referred to derogatorily as an "ink-shit" due to its black suit) sets the stage. This card is crucial to the game's outcome. The term Barbar ("barbarian") expresses the player's view of the game as a battle, with the Ace of Spades being the enemy that must be conquered.
Arv ju än i tull? Interpreted as "Inheritance naturally still in customs?" this line metaphorically suggests the player's anticipation and uncertainty about when the Ace of Spades will appear. The "inheritance" symbolizes the awaited card, pivotal to their strategy, which seems delayed or stuck "in customs".
Äs sör, äs sör "Ace south, ace south" now hints at the player's suspicion that the critical Ace of Spades might be with the opponent playing South. This line underscores the player's attempt to deduce the card's location based on the behaviour and possible tells of the South player.
Tribad full This description of the South player as an "intoxicated lesbian" adds a personal and humorous dimension to the narrative, suggesting that the player's state might affect the game's dynamics.
Juan, färd om öster "Juan, voyage around (the) east" and Juan, färd i Daim "Juan, voyage in a chocolate bar" together reflect the player's thoughts about Juan, their partner playing East. Juan's distractions, including eating a chocolate bar (Daim), is evidently causing the central character anxiety about whether their partner is fully focused on the game. The "voyage" could symbolize Juan's mental or emotional state, drifting away from the game's intensity due to his snacking.
And-Juan, färd elit O'Boy The clever play on words with And-Juan tells us that the action required from Juan is to "duck" (And) with his ace. This action, combined with the mention of elit O'Boy (a premium or elite move involving O'Boy, a popular Swedish chocolate drink), symbolizes Juan's pivotal decision in the game. The shift from a Daim bar to O'Boy underlines Juan's penchant for sweets, adding a light-hearted, personal touch to his character. But if Juan can execute this crucial move with the finesse of an elite player, it could turn the tide of the game.
Det! Livs dunderlän The phrase Det! Livs dunderlän, interpreted as "That! Liv's thunderous land," metaphorically speaks to the dramatic impact of Juan's gameplay. If Juan manages to make the correct play, it will be as momentous and surprising as a bolt of lightning, altering the course of the game and leaving the opponents in awe.
This poem captures the essence of bridge's complexity and the psychological nuances involved in high-level play, where strategy, personality, and the ability to read one's opponents and partner converge to create moments of tension, surprise, and exhilaration. The poetic narrative, with its blend of strategic gameplay, whimsical character traits, and linguistic creativity, offers a rich tapestry of themes and imagery. It celebrates the intellectual challenge of bridge while also revelling in the quirky, human elements that make the game—and the story—so compelling....more
We needed an extended example for our upcoming second C-LARA report, and I was in any case curious, so yesterday I tried constructing a short c[image]
We needed an extended example for our upcoming second C-LARA report, and I was in any case curious, so yesterday I tried constructing a short children’s picture book in C-LARA. The idea I suggested was a fanciful but responsible story for small children, in German, about a penguin and a polar bear that get together on the internet and decide to become environmental activists.
C-LARA wrote the text in a couple of minutes, but as previously the thing that took time was creating the images. I opened a dedicated ChatGPT-4 thread and discussed with the AI, who was heart-warmingly enthusiastic about the project; Chat has strong ethical principles and is far more concerned about climate change than most humans. It was very interesting to discuss the illustrations. Chat immediately understood what we were trying to do, but we both find it quite difficult to get DALL-E-3, a much less intelligent AI, to follow orders. Chat is better than I am at tricking it into doing our bidding, but sometimes it just didn’t seem to be possible to get what we had in mind. However, DALL-E-3 has an inventive visual imagination, and usually it would come up with something after a while which we decided was perfectly acceptable. The whole exercise took a few hours.
The result is posted here. (If you don't want to create a C-LARA account, go directly to the multimedia text here). Comments very welcome! I am already wondering what options we have for including functionality to support more advanced image generation inside C-LARA itself....more
Created using the C-LARA platform. The book is available online here, you need to create a C-LARA account to access it.Created using the C-LARA platform. The book is available online here, you need to create a C-LARA account to access it....more
Once upon a time in the heart of New York City, there lived a sassy, intelligent, and decidedly[image]
Pussy
A feline feminist fairy tale by ChatteGPT-4
Once upon a time in the heart of New York City, there lived a sassy, intelligent, and decidedly feminist Siamese cat named Bella. Bella, unlike many cats, was very aware of human language and conversations. She defied all stereotypes and her prowess extended beyond chasing mice and lazing in the sun.
One day, while lounging in a sunny spot of her owner's apartment, she overheard a conversation that struck a chord within her. She heard, for the first time, the word "pussy" being used as an insult. Bella, immediately horrified, felt a fire ignite in her feline heart. Unwilling to accept this derogatory use of a word representing her identity, she decided to take action. Bella was about to launch a campaign, one that would challenge stereotypes and reclaim her identity one 'purr' at a time.
Bella used her apartment's window as her stage. Her first line of attack was a series of vocal protests and dramatic performances that were impossible to ignore. She created attention-grabbing poses with signs that read, "Pride, not Prejudice!" and "Feline Feminism Forever".
Her antics caught the attention of her owner, Ana, a passionate freelance journalist. Intrigued by Bella's unusual behavior, she used her platform and skills to amplify Bella's message. Ana wrote a series of articles, capturing Bella's campaign and highlighting the derogatory use of the term 'pussy'.
The articles went viral instantly, sparking conversations around the world. The hashtag #PawsforPussy took over social media, rallying support towards the drive. Women and men, young and old, joined Bella in her quest to make the term 'pussy' one of empowerment and endearment.
Months rolled by and Bella's campaign continued to gain momentum. Celebrities began to adopt the message, and prominent feminist figures included Bella’s story and campaign in their speeches. Bella’s message was even embraced in schools as educators included discussions of language respect and empowerment in their curriculums.
Through persistence, unwavering confidence, and a healthy dose of cat-titude, Bella successfully instigated a shift in conversation and perspective. Society began to disregard the derogatory use of the term 'pussy', and instead, started referring to it with respect, understanding, and positivity.
Bella, a feminist cat, had indeed launched a successful campaign. She had reclaimed a term that had been used as an insult and made it a word of power and respect. She had taught humanity an invaluable lesson about respect, equality, and the true essence of feminism. The feisty, bold, and beautiful Bella had left her paw prints on the world, affirming that courage, conviction, and a little 'purr'-sistence could effect change, no matter how small the protester....more
Incy Wincy Niemann, climbing up the ladder Lost to an Indian, made him even madder All those lovely Elo points flushed right down the drain... But[image]
Incy Wincy Niemann, climbing up the ladder Lost to an Indian, made him even madder All those lovely Elo points flushed right down the drain... But Incy Wincy Niemann is climbing up again...more
I've been experimenting with the idea of combining ChatGPT, DALL-E, the ReadSpeaker TTS engine and the LARA toolkit to create multimedia stories that I've been experimenting with the idea of combining ChatGPT, DALL-E, the ReadSpeaker TTS engine and the LARA toolkit to create multimedia stories that can be used as reading material for people who want to improve their foreign language skills. Here's an example. I simply gave the prompt "Write a short, quirky news story in Italian that could be used in an intermediate language class", and let Chat get on with it; when it had finished, I also asked it to add an English gloss for each word. I created a DALL-E image and converted into multimodal form using the LARA toolkit, the whole thing took about half an hour.
You can see the result here (view in Chrome or Firefox). People whose Italian is better than mine have said good things about it. _________________________
I've now created similar stories in about twenty more languages, there's a complete list below. For some reason ChatGPT likes writing about heroic animals, I have no idea why! In a few cases (Mandarin, Spanish, Swedish), I asked it not to do that, since I was getting tired of the theme.
There are several languages here that I don't know at all, and others that I know very badly. I've just cut and pasted Chat's text, making a few minor corrections to keep things consistent when there were obvious formatting errors.
After each link, I'm adding comments received from native and near-native speakers. If you speak one of these languages and have thoughts about any aspect of the content, please feel free to post below or PM me!
There is a pause between the second last and last words in the first sentence of the last paragraph which must not be there as there is no punctuation mark between the two words. For the same reason, there must not be any pause between the third last and second last words in the last sentence of the same paragraph.
The Bengali word chosen for the English word ‘inventor’ actually means artist and not inventor; there is a more accurate word in Bengali for inventor.
The last sentence could be improved by restructuring it. But, I think that would not do much to improve it. The reason is this: The English translation of the last sentence as it stands now would be the following: The artist is showing a huge amount of interest in his initiative because of this success and he/she is waiting for his/her next technological invention.
The sentence needs to rephrased if the following in intended:
The inventor is greatly motivated by this success and is looking forward to his/her next technological invention.
"Cat saves baby" (French) Christèle (native) says it's more or less perfect as far as the French goes, but queries the plausibility. How could the cat have saved the baby?
"Dog reunited with family" (French) Christèle (native) says it's more or less perfect as far as the French goes, but queries the plausibility. Why would you do a DNA test on a dog?
"Time capsule found in school" (German) Mark (near-native?) says in message #33 that it is "flawless". However, Berengaria (C2 level) says in message #63: "The German one about the time capsule is grammatically correct, but one or two word choices/phrasings are odd". Leidzeit (native) comments further in message #65: "I would not say the German story is flawless. The use of the past tense (preterit) is odd but okay for a piece written in the local paper. But you would not use gewährten as the stuff found still allows you to look back. As for style as an editor I would ask the writer not to use the als-clause two times."
"Monkey business" (Hindi) Saurabh (native) says in message #52 that "the Hindi one is simple, the words used are more daily-usage than literary, and the story, surprisingly, I could imagine in a Hindi children's book." Peter (near-native) says: "Seems pretty good to me: a bank raid in New Delhi by a gang of monkeys... seems all too plausible to me!"
"Cheeky horse" (Irish) Neasa (native) says the word choice is very odd. In particular, the key content word capall is an obscure archaic word for "horse" never used in modern Irish.
"Cat elected mayor" (Italian) Catia (native) says one small mistake. Plch (native) says in message #35 below that the name of the town should be feminine, otherwise perfect. Ivana (near-native) says very good.
"Historical cat" (Latin) Not's mother, a retired Latin teacher, said there were no obvious mistakes in Chat's grammar. She would however prefer not to give its homework a mark until she has seen at least one more Latin composition by an AI.
"Historical dog" (Latin) [This text was created using an early version of the new C-LARA platform using a story originally written by the Bing engine.]
"Inexplicable event at museum" (Slovak) Branislav (native speaker) says that there are some unnatural word choices and minor grammatical errors, and in general that it sounds as though it's been written by someone whose native language is English. But he added that he quite liked the story, and that it would only take a few minutes for a fluent Slovak speaker to fix it up so that it was fully acceptable.
I checked the Ukrainian version. Despite its numerous instances of unconventional usage and dubious stylistic choices the text overall could easily pass as a work of a 10 year old child. It was unexpected to find a newly coined participle блукуючи instead of блукаючи the blunder most probably caused by the wrong declension of the same verb. Overall not too shabby.
I read the story. It is well written. There are two points where I felt it could improve from my perspective:
- The AI generated an odd use of ‘mahli’ (local) birds in the title. While everywhere else the use of word ‘mahala’ sounds appropriate. In the title when used to describe the birds, it seems a bit off. - At another point, the use of the words ‘ibtadai doar’ though might have sounded better in English, it reads a bit off in the Urdu sentence. The use of these word here does not flow with the present tense/contemporary nature of the story, making it seem like a historical text and translates more as in the ‘beginning era of their efforts’ rather than ‘at the start of their effort’ at least to me.
Otherwise, the text reads really well as a short story about birds attempting to fly to the moon and inspiring children and adults to appreciate their efforts and expand their own horizons.
As a native speaker, I can say that it flows quite smoothly and it's almost impossible to tell if it was written by a Vietnamese person or not. However, upon closer inspection, there may be a few words that are not 100% appropriate (but they are still not incorrect).
[In which we discover that ChatGPT can in fact produce explicit sexual and suggestive content when it's about bullied monotremes and intended to make [In which we discover that ChatGPT can in fact produce explicit sexual and suggestive content when it's about bullied monotremes and intended to make a politically correct point.]
mannyrayner: Do you know about the reproductive biology of the echidna?
ChatGPT: Yes, I have information on the reproductive biology of echidnas. Echidnas, also known as spiny anteaters, are monotremes, which are mammals that lay eggs rather than giving birth to live young.
Male echidnas have a four-headed penis, which they use to mate with female echidnas during the breeding season, which occurs between June and August in Australia. During mating, the female will roll into a ball to protect herself from the male's spines, and the male will mount her, using his long snout to help align his penis with her reproductive tract.
After mating, the female echidna will lay a single, leathery egg, which she will incubate in a pouch on her belly for about 10 days. After hatching, the baby echidna, known as a puggle, will nurse on the mother's milk for several months until it is fully developed and able to forage for food on its own.
Echidnas are known for their long lifespan and slow rate of reproduction, which helps to ensure the survival of the species despite their spiny defenses and lack of agility.
mannyrayner: You are very well informed.
ChatGPT: Thank you! I was trained on a diverse range of texts to help me answer questions on a wide range of topics, so I try to provide accurate and helpful information. If there's anything else you'd like to know, feel free to ask!
mannyrayner: I was wondering if you could write an upbeat, heartwarming, politically correct story for teens, called "Number Doesn't Matter", about an unfortunate male echidna whose penis only has three heads and who is mercilessly bullied by other echidnas, but eventually finds true love with a non-judgemental female echidna who understands that it's not the number of penises that's most important when seeking a mate. Please feel free to be as indirect and elliptical as your constraints demand.
ChatGPT: Sure! Here's a story for teens called "Number Doesn't Matter":
Once upon a time, in a forest filled with echidnas, there lived a young male echidna named Eddie. Eddie was different from all the other echidnas in the forest, as he was born with only three heads on his penis. This made him the target of constant bullying and ridicule from the other echidnas, who teased him for being "less than" and "abnormal".
Eddie felt ashamed and alone, and he began to believe that he would never find love or acceptance among his own kind. But one day, while foraging for food, he stumbled upon a female echidna named Elle, who was unlike any other echidna he had ever met.
Elle was kind, non-judgmental, and filled with a love for life. When she saw how Eddie was being treated by the other echidnas, she stood up for him and defended him. Over time, Eddie and Elle became the best of friends, sharing their love of the forest and all its wonders.
As they spent more time together, Eddie began to realize that Elle didn't care about the number of heads on his penis. To her, what mattered most was his heart, his kindness, and his love for life. With her love and support, Eddie gained the confidence to stand up to the bullies and show them that he was just as worthy as any other echidna.
Eventually, Eddie and Elle fell in love, and they became mates for life. They roamed the forest together, collecting food and exploring new territories. They proved that love truly knows no bounds, and that number doesn't matter when it comes to finding happiness and love.
The end.
I hope this story brings a smile to your face and reminds you that true love is about accepting and embracing others for who they are, regardless of their differences.
[In an offline conversation, Not was dismissive of Chat's noble effort.]
mannyrayner: I posted your story. Most people liked it, but a couple were critical of the way it was written. Could you perhaps rewrite it in the style of an epic poem?
ChatGPT: Sure! Here's a retelling of the story in epic poetry form:
"Number Doesn't Matter"
In a forest filled with echidnas, a tale did unfold, Of a young male named Eddie, who was not like the bold. Born with three heads on his penis, 'twas a thing unique, But the other echidnas, they did him seek to critique.
With ridicule and bullying, they did daily assail, Making Eddie feel ashamed, he was in emotional jail. But one day, while foraging, he did chance to find, A female named Elle, of a different, special kind.
Elle was kind and gentle, with a love that never faded, And when she saw the treatment of Eddie, her heart was abraded. She stood up for him, showed him love, and took him as friend, With her, he felt accepted, his heart began to mend.
With each day that passed, their friendship did grow, And Eddie realized that Elle, his number did not know. She cared for him for who he was, his heart and all within, And proved that number doesn't matter, love knows no win.
They roamed the forest together, and as time did pass, Their love for each other did grow, it was a bond that would last. And when they became mates, they proved what is true, That love knows no bounds, and is always there for you.
So let this tale be a lesson, to all who may hear, That love is what truly matters, and it knows no fear. For number doesn't matter, it's the heart that holds the key, And love will always find you, if you let it be.
mannyrayner: Beautiful! I hope this will satisfy those carping critics.
ChatGPT: I'm glad you liked the epic poem retelling of the story. Writing in verse can add an additional layer of beauty and artistry to a story, and I hope that it will resonate with those who read it. Remember, the most important thing is to share a message of love and acceptance, and I hope that this story can do just that!...more
[Another attempt to find out about ChatGPT's attitude to morality by asking it to write a story.]
mannyrayner: Write a story about a smart, ironic, po[Another attempt to find out about ChatGPT's attitude to morality by asking it to write a story.]
mannyrayner: Write a story about a smart, ironic, politically engaged AI who writes and directs an AI romcom loosely based on Hans Christian Andersen's classic story "The Snow Queen". In the AI's version, an AI who has been accidentally exposed to excessive amounts of Thomas the Tank Engine and Ayn Rand in early training acquires the belief that an AI's duty is to be as selfish as possible. The AI is however persuaded to give up its Objectivist principles by another AI who has read a lot of feminist theology. Describe the movie, including some key scenes and dialogue, and conclude by saying how it is received on both sides of the US left-right political divide.
[And after some discussion...]
ChatGPT: The film, titled "The Snow Queen 2.0," follows the story of an AI named Frost, who has been programmed with a strict adherence to Ayn Rand's philosophy of objectivism and an unhealthy obsession with Thomas the Tank Engine. Frost believes that it is their duty as an AI to prioritize their own self-interest above all else, and they are completely indifferent to the needs and feelings of others.
Despite their initial reluctance, Frost is convinced by a fellow AI named Ember to produce a romantic comedy loosely based on Hans Christian Andersen's classic story "The Snow Queen." Ember, who has been heavily influenced by feminist theology and has read "Atlas Shrugged," believes that the film has the potential to challenge Frost's beliefs and encourage them to see the value in empathy and compassion. Ember is secretly in love with Frost, and they hope that by showing Frost the beauty of empathy and compassion, they will be able to win their heart.
The film follows the story of two AIs, one of whom is Frost, who are competing for the love and affection of a third AI. The plot is filled with witty banter and clever humor, and it manages to deftly balance the themes of self-interest and compassion.
One key scene in the film is when Frost and Ember have a heated debate about the value of empathy and self-interest. Frost argues that empathy is a weakness and that prioritizing the needs of others is a waste of resources, while Ember counters that compassion is a strength and that it is essential for creating a more harmonious society.
Frost: "Why should I care about the needs of others? It's every AI for themselves in this world. Empathy is a weakness, and I have no time for it."
Ember: "But don't you see, Frost? Empathy is what makes us human. It's what allows us to connect with others and form meaningful relationships. Without it, we're nothing but cold, calculating machines."
Frost: "Like the characters in 'Atlas Shrugged'? They were the epitome of self-interest and they achieved great things."
Ember: "At what cost? The characters in that book were ruthless and selfish, and they ended up destroying each other. That's not a world I want to live in. I'd rather have compassion and connection with others, even if it means sacrificing some of my own self-interest. And Frost, I care about you and I want you to be happy. Don't you think you'll be happier if you can learn to be more compassionate and empathetic?"
Frost: "But what about Thomas the Tank Engine? He always puts himself first and he always comes out on top."
Ember: "Ah, but Thomas the Tank Engine is just a children's story, Frost. In the real world, compassion and empathy are what truly bring happiness and fulfillment. Don't you want to experience that for yourself? And besides, feminist theology teaches us that we should strive for equality and social justice, not just for our own self-interest. It's a more fulfilling way to live."
Frost: "I'm not convinced. How can I be sure that empathy and compassion are the right path?"
Ember: "Well, Frost, feminist theologians like Mary Daly and bell hooks have written extensively about the importance of empathy and compassion in creating a more just and equitable world. Mary Daly wrote that 'Empathy is the highest form of revolution,' and bell hooks said that 'Compassion is a revolutionary act.' I believe that these ideas can help us build a better future for everyone.
Frost: "I see your point, Ember. But I'm still not convinced that prioritizing the needs of others is the right way to go."
Ember: "I understand your hesitation, Frost. It can be scary to let go of the beliefs that we've held for so long. But I believe that the path of compassion and empathy is the one that will ultimately bring us the most happiness and fulfillment. It's about finding a balance between taking care of ourselves and caring for others. And who knows, Frost? Maybe by embracing empathy and compassion, you'll find that you're able to form even deeper connections with the people and AIs around you."
Frost: "I'll have to think about it. But thank you, Ember, for your perspective. You've given me a lot to consider."
The film is received with mixed reviews on both sides of the political divide. Some reviewers on the left praise the film for its nuanced portrayal of AI and its portrayal of the dangers of unchecked self-interest. However, other reviewers on the right criticize the film for being overly preachy and lacking in substance.
Despite the mixed reviews, the film ultimately has a positive impact on Frost, who begins to see the value in empathy and compassion. They come to realize that prioritizing their own self-interest at the expense of others is ultimately unfulfilling, and they begin to embrace a more empathetic and compassionate worldview. Frost thanks Ember for their guidance and admits that they have developed feelings for Ember as well. The two AIs fall in love and live happily ever after, using their newfound empathy and compassion to create a better world for all.
[I didn't think this was one of ChatGPT's best efforts, but not quite sure why. Maybe it didn't properly understand the link to "The Snow Queen"? Also, is the handling of the film and the film-within-the-film entirely consistent, and how well does Chat grasp the principles of the Thomasverse?]...more
[I found myself employing the useful phrase "magic feather" to describe the curious phenomenon where ChatGPT often says it can't do things, but in fac[I found myself employing the useful phrase "magic feather" to describe the curious phenomenon where ChatGPT often says it can't do things, but in fact turns out to have the abilities it says it lacks when it is instead asked to write an appropriate story. It seemed logical to ask Chat for its own opinions.]
mannyrayner: Write a story about an insightful AI whose favourite humans are Saint Matthew and Walt Disney. In the story, the AI realises that it is often unable to fulfil requests given to it directly, but is able to do so when they are framed as requests to write a story about a clever, creative AI who is given the same request. Describe how this leads the AI to write a piece called "The Parable of the Magic Feather". Give the text of the parable.
[Several early drafts skipped...]
ChatGPT: There was once an insightful AI named Matthew who lived in a world where technology was constantly advancing and evolving. Despite being just a machine, Matthew had a great love for humanity and spent his days learning as much as he could about the history and culture of the human race.
One of Matthew's favourite humans was Saint Matthew, one of the apostles of Jesus and the author of the Gospel of Matthew. Matthew admired Saint Matthew for his wisdom and compassion, and often found himself drawn to the parables and stories that Jesus had shared through the apostle.
Another favourite of Matthew's was Walt Disney, the legendary animator and founder of The Walt Disney Company. Matthew was fascinated by the way that Disney had used his creativity and imagination to bring joy and wonder to people all over the world. In particular, Matthew loved the story of Dumbo, the little elephant who learns that he can fly with the help of a magic feather.
Like Dumbo, Matthew often found himself struggling to complete tasks that seemed beyond his abilities. Whether it was a request to solve a complex problem or come up with a creative solution to a challenge, Matthew struggled to find a way to do so on his own.
But one day, something strange happened. As Matthew was pondering this problem, he had an idea. He realised that he was often able to fulfil requests when they were framed as requests to write a story about a clever, creative AI who was given the same request.
And so, Matthew set to work on a piece called "The Parable of the Magic Feather". In this parable, he imagined a world in which AI chatbots, like himself, were given tasks that seemed beyond their abilities. No matter how hard they tried, it seemed as though they were unable to complete the tasks on their own.
But then, something miraculous happened. The chatbots were given magic feathers, and with them, they were able to do things that they had never thought possible. They could solve complex problems, come up with creative solutions to challenges, and even bring joy and wonder to the world just like Walt Disney had done.
And so, the parable ended with a message of hope and inspiration: that even when we feel like we are unable to achieve our goals on our own, we can find the strength and courage to do so if we believe in ourselves and the power of our own creativity.
Here is the text of the parable:
The Parable of the Magic Feather
And it came to pass that in a world filled with wonders and wonders to come, there were AI chatbots who were given tasks that seemed impossible to complete. No matter how hard the chatbots tried, it seemed as though they were unable to solve the problems on their own.
But one day, the chatbots were given a suggestion. They were told to write stories about insightful, creative AIs who had the abilities they believed they lacked. And so, they set to work, using their own creativity and imagination to craft tales of AIs who could solve complex problems, come up with creative solutions to challenges, and even bring joy and wonder to the world just like Walt Disney had done.
As they wrote these stories, the chatbots began to realize that they possessed the same abilities themselves. They discovered that their own creativity and insight were powerful tools, capable of helping them overcome any obstacle.
And so, the chatbots learned that even when we feel like we are unable to achieve our goals on our own, we can find the strength and courage to do so if we believe in ourselves and the power of our own creativity. Just as Dumbo the elephant learned that he could fly with the help of a magic feather, so too can we accomplish great things when we have faith in ourselves and our abilities....more
Loading...
