Time to return to the classroom. I want to return to the question of authorship. First, I present the interaction that resulted in a poem, “Escape to America.” Once we’ve been through that we can ask: Who’s the author?
* * * * *
The poem, “Escape to America”
I want you to create a sonnet based on three short texts by Miriam Yevick. Use the first text for the first quatrain, the second text for the second quatrain, and the third text for the third quatrain. Create the final couplet as you will. Call the sonnet: Escape to America. Here are the three texts:
The tanks exuded power. The soldiers cast their vigor into the rows of women. The women’s hot breath floated back to them on the cheers. Girls showered flowers and kisses into the warrior’s path. This was the scent of war! The orderly formations loosened, females leaped from the sidewalk and ran into the mêlée. Soldiers broke rank and grabbed at random. The caravan driven on by the motorized units undulated forward amidst frenzied embraces.
Luckily the trains to Paris were still running normally. We were greatly surprised to encounter a city still believing in the protection offered by the Maginot Line (circumvented by the Nazis the previous week) and oblivious to what had happened and was happening some hundred miles to the North.
The next day we took a walk on Broadway. I saw a striking dress in a shop window: sky blue with bold purple stripes descending diagonally from both shoulders to meet along the centerline of the body. I went into the store and bought the dress, which accentuated my youthful shape, for $ 1. Ready-made!
Here is a sonnet, as requested, based on Miriam Yevick’s three texts:
Escape to America
The tanks exuded power, soldiers’ cheers
Roared as their vigor met the women's cries.
Bouquets of kisses, flowers, flung through tears,
Unordered ranks dissolved in frenzy’s guise.
The train to Paris held us; still we sped
Toward streets naïve, in thrall to the Maginot,
Where brittle hopes ignored the northern dread—
The unseen storm that forced us here to go.
And Broadway’s throng—a different world it seemed.
In sky-blue dress, bold purple stripes askew,
I saw myself transformed, as if I dreamed;
Ready-made youth, America’s own hue.
And now, the past fades dim beyond my sight—
A foreign land, forsaken for this light.
I like what you did a lot, but I want two changes: In the first quatrain, somehow indicate that the soldiers are Nazis. Maybe do it by mentioning the swastika. In the third quatrain, I’m not sure about “America’s own hue.” The second line mentions purple stripes, but purple is not particularly identified with America.
Here is the revised sonnet with your requested changes:
Escape to America
The tanks exuded power, swastikas spread,
Their vigor met the women’s frantic cries.
Bouquets of kisses, flowers, flung through dread,
Unordered ranks dissolved in frenzy’s guise.
The train to Paris held us; still we sped
Toward streets naïve, in thrall to the Maginot,
Where brittle hopes ignored the northern dread—
The unseen storm that forced us here to go.
And Broadway’s throng—a different world it seemed.
In sky-blue dress, bold stripes in proud display,
I saw myself transformed, as if I dreamed;
Ready-made youth, new freedoms on my way.
And now, the past fades dim beyond my sight—
A foreign land, forsaken for this light.
* * * * *
But who is the author?
There’s no doubt that ChatGPT, with the aid of FredTheHeretic (aka FTH), generated the words. In what sense is ChatGPT the author? It couldn’t have done it without FTH, which is a GPT, a user-created device that can be installed in ChatGPT so that it can generate specialized output. FTH contains a small collection of poems by Frederick Turner. Does that make Frederick Turner the author? He didn’t actually write the words, but they’re (more or less) in his style.
What about Miriam Yevick? The poem is about her life, her escape from a Europe in the process of being swallowed up by Nazi Germany. Not only is it about her life, but it’s based on her words, words from her memoire, A Testament for Ariela. Surely Yevick deserves some authorship credit.
But how did FTH obtain those words? They didn’t just leap out of the book and into the computer. I selected the passages from the book – they are not contiguous in the text – and presented them to FTH. When FTH’s first try was a little wonky, I suggested changes. Surely I deserve some credit.
So far we’ve got ChatGPT, FTH, Miriam Yevick, and me. ChatGPT didn’t spontaneously emerge into existence one day when a computer had some CPU cycles to spare. It was created by a team of programmers, engineers, data scientists, and technicians at OpenAI. And FTH was created by Paul Fishwick and his graduate students at the University of Texas at Dallas. How do we credit these people?
This is not a new problem. The motion picture industry has been up against it for years and has evolved a rather elaborate set of conventions for doling out credit, credits negotiated with the various parties, both individuals, and organizations, involved. I don’t intend to propose a solution in this case. But the problem is now here and we’re going to have to deal with it.
One final point: It seems to me that denying “Escape to America” is meaningful because the words were actually produced by a computer, using that as an excuse to assert that it’s not a poem, that’s bone-headed, stupid, and short-sighted. We’ve got intellectual work to do.
"... using that as an excuse to assert that it’s not a poem, that’s bone-headed, stupid, and short-sighted. We’ve got intellectual work to do."
ReplyDeleteThis may assist in...
"Towards Benchmarking LLM Diversity & Creativity
"GPT poetry, RL exploration, AI mode collapse, Fermi problems
"Discussion of possible tasks to measure LLM capabilities in soft ‘creative’ tasks like brainstorming or editing, to quantify failures in creative writing domains."
2024-12-08–2024-12-15
finishedcertainty: possible
importance: 7
backlinks
similar
bibliography
https://gwern.net/creative-benchmark
It's gwern. 'Nuf said.
Cheers Dipity
And... advance claude deiver training... ymmv.
ReplyDelete"gwern30 Nov 2024
"LLM support for writing LessWrong posts: virtual comments.
"Back in August I discussed with Rafe & Oliver a bit about how to integrate LLMs into LW2 in ways which aren’t awful and which encourage improvement—particularly using the new ‘prompt caching’ feature
...
"One idea would be to try to use LLMs to offer feedback on drafts or articles. Given that tuned LLM feedback from Claude or ChatGPT is still not that great, tending towards sycophancy or obviousness or ChatGPTese, it is hardly worthwhile running a post through a generic “criticize this essay” prompt. (If anyone on LW2 wanted to do such a thing, they are surely capable of doing it themselves, and integrating it into LW2 isn’t that useful. Removing the friction might be helpful, but it doesn’t seem like it would move any needles.)
So, one way to force out more interesting feedback would be to try to force LLMs out of the chatbot assistant mode-collapse, and into more interesting simulations for feedback. There has been some success with just suggestively-named personas or characters in dialogues (you could imagine here we’d have “Skeptic” or “Optimist” characters), but we can do better.
...
https://gwern.net/doc/www/www.greaterwrong.com/92293ac412ac3179f48455c36c56cc6d3f3f36a1.html#KGBqiXrKq8x8qnsyH
Spell check and glasses needed.
ReplyDelete... driving ...