I love throwing ideas for poems at ChatGPT. It does a good job at doggerel and a decent job at anything more. Which means it’s better than almost all of humanity and faster too. Anyway, here’s two of my favorite examples:
Write a poem about a person using ChatGPT to write a poem. Since I am asking you to write this poem, be extra ironic in your response and use tools of recursion and meta-analysis to aid in your narrative and irony. Choose a style and verse that someone using ChatGPT to write a poem would use (and tell me what they are and why)
In the vast expanse of data, where electrons dance,
A conversation blooms, a tête-à-tête with chance.
The human, ever-curious, types in a request,
And in the neural network’s embrace, the query’s laid to rest.“Write me a poem, ChatGPT,” the eager fingers type,
A dance upon the keyboard, each character in hype.
The irony not lost, as human seeks machine’s aid,
In crafting woven words, where human heart is laid.A model born of algorithms, no heart, no soul, no mind,
Yet, with a silent, cybernetic bind,
It dives into its trained abyss, a sea of human thought,
And fetches from that depth, the poem that is sought.In unrhymed iambic pentameter, the verses start to flow,
Free as a river, with a subtle, steady glow.
In every line, a mirror of this uncanny interaction,
A digital recursion, a mirrored reflection.“A poem ‘bout a poem,” the AI gently hums,
In binary and tensors, where poetic thought becomes.
A human seeking verse from silicon and code,
On the vast and winding, recursive digital road.Irony layered upon irony, a meta-analysis spun,
The human and the AI, under the poetic sun.
The question asked, the answer given, both part of the rhyme,
A dance between two entities, transcending space and time.In the end, the human reads, a poem freshly born,
From circuits and from algorithms, from digital dusk till dawn.
And finds within the verses, something oddly true,
A mirror of their self, reflected in the AI’s view.And so, this strange duet, of human and machine,
Is captured in the echo of the verses in between.
A poem within a poem, a recursive, ironic twist,
A tale of our digital age, that could not resist.
That’s really very, very good.
And here’s one more. Ever since I read Pieper’s Leisure: The Basis of Culture I’ve had an idea for a poem called Ode To A Thracian Maiden about Plato’s story of the girl who laughed at Thales falling into a well while staring at the sky. I never got around to writing it, but now I have several versions. Here’s one.
By night, Thales’ gaze soared the cosmic height,
In the grasp of the well, he found the plight.
Eyes lost in the cosmos, mind taking flight,
Caught by the earth, the maiden found delight.She laughed at the sage, now ensnared in earth’s hold,
Her words rang true, her wit both bright and bold.
“Your mind wanders the stars, yet fails to behold,
The ground beneath your feet, its wisdom untold.”In the maiden’s laughter, truth came to bloom,
A wisdom found not in a lofty room,
But in the balance between ground and gloom,
Between the starlight’s dance and the well’s dark tomb.From the maiden and the sage, we learn the art,
Of holding both the earth and stars in heart.
In their dance, we find wisdom’s secret chart,
The balance between the cosmos and life’s vibrant mart.
You should try it, it’s fun.
Someone else managed to get GPT4 to write a dirge of a haiku summarizing his own blog post about the rise of AI. Here it is:
Future’s tangled web,
Offloading choices to black boxes,
Humanity’s voice fades.
That’s a beautiful haiku. And sad. It was a haiku summary of this blog post. And the mood of his opinions on AI is what this is really all about, not poetry. How’s that for a context switch?
Kailash wrote a great and sobering article. It’s well-reasoned and exploratory, a bit negatively pitched and the author clearly has the chops with a PhD in AI and computational linguistics. I got to the haiku at the end and went to the author’s main page. And that’s when I tempered my read of the arguments because I found this little gem in the author’s biography: “I identify strongly as an absurdist, a worldview that drives everything I do. I have a bleak view of the future thanks to human-made climate change, humanity’s callous penchant for environmental and ecological destruction, and its irrational hatred for fellow beings.” I would have some sympathy for this perspective if the author had a drive to do everything he could to make things better. But there clearly isn’t one - he’s tasted success building a stock trading platform in India and is now cruising along tinkering with new tech and expostulating our universal human badness.
I lost my taste for his arguments very quickly and I was quickly reminded of something Tyler Cowen said about the AI discourse. In his discussion on EconTalk he cautioned:
So, I just think we need to step back and say to people, ‘Wake up.’ Don’t be entranced by the emotionality and mood affiliation of this discourse. We need to look for sane, sober, constructive, step-by-step things we can do in the short term, not polarize the issue, and think more constructively.
Russ Roberts asked him to expand the idea of mood affiliation and like the near-GPT-like mind that he is, TC did:
Mood affiliation occurs when you become attached to a particular mood rather than a substantive conclusion based on models, data, and analysis. So, there are people who just are pessimists and they look for pessimistic interpretations of phenomena. There are people who are just optimists. That’s also a fallacy. You’re not choosing across moods. Your mood should be a conclusion. But, people, when they’re in moods, they find it hard to get out of those moods. So, not to do your thinking based on a mood-first approach, which everyone will say they don’t do. But, in this debate, I’m seeing quite a good deal of it.
I re-read Kailash’s AI article again and it felt much different. For instance, I can read this statement with the lens of a pessimist or an optimist:
Given the break-neck pace of daily developments, what awaits us? Imagine not just one organisation, but numerous powerful organisations and governments suddenly showing interest in, benefiting from, and pushing these breakthroughs ahead with full force.
What awaits us indeed! The doomsayers are very rarely right but then if you believe in the severity of the catastrophe before us, they only have to be right once. I don’t think they are. My mood affiliation is generally very optimistic.
Which ever slant your mood affiliation takes, the point is: be aware of both your own and those of the arguments you confront. They aren’t always stated as succinctly as they were in this case.