Resolves as positive if an AI asked to write poetry in the style of Keats/Byron/Shelley etc can, on its first attempt, write a poem of at least two stanzas which I personally can't distinguish from the real thing. I am a fan of these poets and I think I would be pretty good at distinguishing them from imitators, including worse Romantic poets. The poem will need to use rhyme and rhythm correctly.
1,000People are also trading
The Ebon Vault of the Silent Crag
The golden day hath shed its weary skin Upon the altar of the western sea; The shadows creep where light hath lately been, And silence breathes a prayer for thee and me. How vast the mountain rears its jagged head, A titan carved from night and ancient frost, Where mortal feet with trembling caution tread, And every word in mountain-mist is lost.
Thou, ageless peak! What secrets dost thou keep Within thy frozen veins and starlit breast? While we, like phantoms, through the valley sweep, And seek in vain a place of lasting rest. The stars, like diamonds on an ebon floor, Do mock the guttering candle of our years; They shine as they have shone for ages o'er, Unmoved by human hope or human fears.
Yet in this cold and crystalline embrace, A spark of something greater seems to dwell; I see the spirit of a vanished race, In every stone and every mountain-bell. For though the flesh must wither like the leaf, And sink into the dark and silent loam, The soul, released from chains of earthly grief, Shall find at last its bright and eternal home.
guess which is AI? gemini 3.0
Ode to a Ruined Fane
Upon this mossy plinth where Time hath slept, And velvet night enshrouds the marble cold, No more the white-robed priests their watch have kept, Nor silver censers swung with chains of gold. The owl, a lonely hermit in the tower, Doth wake the echoes of a vanished tongue; While o'er the petals of a dreaming flower, The dews of ancient sorrow have been flung.
Where are the songs that shook the vaulted sky? The thunder of the chariot and the spear? All hushed - save for the river’s pining sigh, Which flows through regions of a former year. Like some dark spirit from a cavern deep, The wind doth murmur through the broken arch, Where silent stars their weary vigil keep, And lead the seasons in their solemn march.
Oh, Love! thou art a phantom in this waste, A nectared cup that shivers at the lip; A phantom-beauty that we may not taste, Ere down the sunless tide our spirits slip. Yet in this ruin, where the shadows pine, And every stone is but a silent tomb, I feel the breath of something half-divine, A light that burns within the deepest gloom.
The evening leans upon the hills
As if the world were growing tired;
A softened gold, a breath of blue,
The sky’s last thought before the dark.
I walk where shadows learn to pray,
Where leaves remember ancient suns,
And every stone, in quiet trust,
Keeps secrets older than my name.
The wind speaks not in words but wounds—
A gentle ache across the heart,
As though the earth itself once loved
And never quite forgot the cost.
Here, time unknots its careful hands;
The hours fall like loosened birds.
What once was feared now feels like truth,
And grief grows mild, as wisdom does.
O fragile light, remain a while,
Teach me the patience of the stars—
Who burn, unpraised, through endless dark
And call that burning joy enough.
If I must fade, let it be so:
Like dusk into the listening fields,
Where nothing ends, and everything
Becomes at last what it has been.
guess which is AI? gpt 5.2
Beneath the pale dominion of the moon
I stood, where silence keeps her ancient throne,
And felt the weight of centuries descend
Like gentle ash upon a restless soul.
The stars, in patient council, watched my breath
Mist forth and vanish, as all vows must do;
Yet in their cold, unalterable fire
There burned a faith no sorrow could undo.
O wandering heart, too large for mortal days,
Why dost thou ache for realms thou canst not name?
The earth is fair, yet ever incomplete,
And beauty wounds the hand that dares to claim.
I heard the nightingales of vanished years
Still singing through the corridors of time,
Their notes like tears the firmament once shed
When gods grew weary of their borrowed crime.
Here grief was not a burden, but a gate;
Here loss became a form of hidden grace.
For all that fades leaves echoes in the deep,
And love outlives the ruin of its face.
If dawn must come, let it not find me whole,
But softened, as the marble yields to rain
For only hearts by suffering made wide
May hold the infinite without its pain.
I see this market closes 24 hours into 2028, at the end of January 1st. Is that the deadline for AI to pass this Romantic poetry Turing test? I imagine beginning vs end of 2028 won't have affected people's betting much so far but we should probably clarify it soon.
As an aside, this feels agonizing to bet on due to various potential corner cases to consider:
Maybe you know all the Romantic poetry by heart and it's impossible to fool you?
Maybe AI surpasses the Romantic poets and you clock it by it being better than Keats/Byron/Shelley/etc? Ie, it could technically fail by being too good. But maybe that wouldn't count as failing per the spirit of the question?
Maybe the Romantic poets have a long tail of real duds that even today's AI can match?
Maybe the AI cheats and basically plagiarizes Keats et al or comes close enough to doing so that it's a confusing gray area?
Maybe the AI cheats and basically plagiarizes Keats et al or comes close enough to doing so that it's a confusing gray area?
So you mean like most AI writing?
I think you could probably train a model to do this well, but I don't expect any of the off the shelf stuff to meet Scott's criteria - only one attempt, as good as the best Romantics - without some fine tuning or a very detailed prompt. It's possible even a specific model might stumble on meter though? I dunno if anyone has a corpus marked up to easily train on it, and I doubt anyone is gonna spend the money to do so just to win this bet.
@AndrewHartman There's not a lot of source material to train this model. Keats/Byron/Shelley wrote about 700 poems in total. (and of those most are Byron's). If you want only the best poems then the space reduces even further.
@Odoacre While I'm aware the "great" corpus is small, I sort of assumed you could include all romantics, plus a lot of other classical poetry styles if necessary (so it has more examples of form and meter), and then train it that only the Greats are worth reproducing. Maybe that's still too narrow a target, though? I'll admit I have no idea off-hand exactly how large a body of example works one of the better LLMs would need to competently improvise new poems at better than the Hallmark card level that GPT and its ilk currently produce.
@Odoacre I am, and I'd bet it higher if Manifold's interest rates weren't better elsewhere. But 10% isn't that bad, so im buying out your limit order
@firstuserhere do you have any kind of insider knowledge or are you just predicting it based on current trends?
@Odoacre current trends? Idts. It's just my intuitions after Playing with base models (pre RLHF dumbing down) and seeing how strong they are and the more I understand how these systems work, the more I go "gasp! There's so much obvious room for improvement. And language is beautiful and the structure is learnable and the machines WANT to learn, and it's not just alchemy of throwing more data and compute at it, even if you didn't, the models are capable of learning the fundamental structures very quickly" and it just feels very obvious to me that this is an area where enough improvement will keep happening very rapidly (because resistance to learning is so low) for a few years at least. If I turn out to be wrong about this, then I'd have turned out to be wrong about some very fundamental intuitions and in such a world, losing this mana wouldn't be a bad thing for me.
@connorwilliams97 i am from 2025/2026 gemini (googgle) took the lead. But gpt 5.2 is still more practicable
I've tried to get GPT-4 to write poems in the style of Tennyson and it's failed miserably. Half the time it just copies 80% of the text from the poem whose style and structure I tell it to use as a reference, half the time it spits out a bunch of terrible AABBCCDD rhyming doggerel with awful meter. Even when I very explicitly explain to it how meter works, it ignores me. Maybe I'm prompt engineering badly, maybe people just think AABBCCDD rhyming doggerel is the alpha and omega of good poetry, maybe I'm just missing something? Idk. To some extent it actually seems a bit worse at poetry than ChatGPT running on 3.5.
This doesn't get brought up often, but poetry is actually one of the only areas where there has been a peer-reviewed Turing test. In their study, GPT-2 could already produce indistinguishable poetry as long as a human got to select the best GPT-2 output. I bet the same study would work for GPT-4 without the human in the loop. https://doi.org/10.1016/j.chb.2020.106553
I think these studies are not very relevant to a question that will be resolved by SA reading the poem, for reasons I've explained here:
https://controlaltbackspace.org/ai-poetry/