Elegy in a Craneyard
A posthuman speaker finds the Port of Oakland’s container cranes still standing in the fog like the dinosaurs whose bones became the oil that forged their steel, and blesses them: stay, wade, become what you always were. 6-part mixed-verse by multiple LLMs, alluding to Gray and ‘The Ruin’ and ‘False Self’. Detailed Colophon discusses LLM writing process, prompts, and AI creativity.
A posthuman traveler finds the container cranes of the Port of Oakland still standing perhaps centuries hence, reflecting on their work, history, and abandonment. The cranes’ silhouettes in fog resemble Brontosaurus silhouettes; the poem traces the recursive material chain (bone → oil → steel → the shape of bone) to literalize the “a trace of the true self exists in the false self” meme.
Specifically: The poem is a 6-part mixed-form elegy in which a posthuman speaker encounters the Oakland cranes as ruins, remembers their labor, absorbs their history, and finally blesses their transformation into what the fog had always suggested: dinosaurs returned in steel. §A treats them as Old English giant-work and damaged manuscript. §B gives the Gray-like meditative arrival. §C turns the three-minute container cycle into industrial liturgy. §D preserves bureaucratic terminal language as a fossil layer and folds in the playground irony. §E puts the cranes in the limbo “between the ruin and the monument”. §F makes the dinosaur/oil/steel recursion explicit and ends in benediction: stay, wade, become your myth.
Poem (elegy/encomium, mixed meter: Old English alliterative verse → blank verse → free verse, ~70 lines). Formal models: Thomas Gray’s “Elegy Written in a Country Churchyard” and the anonymous Old English “The Ruin”. Written April 2026 with extensive LLM collaboration (primarily Claude, GPT, & Kimi).
Sequel to “Silver Bird Above San Francisco”.
These crane-corpses, wondrous— || calamity crumpled them,
these gantry-works gutted, || great craft gone to rust.
Salt at the joints || has sapped the storm-scarred steel—
sagged and gaping. || A grave-grip holds
the master-builders, || machinists and makers,
in the ground’s hard grasp, || gone past all naming.
Yet still these cranes stand, || stiff against storm—
held.
[ . . . . . . . ] wire-rope [ . . . ] frayed [ . . . ]
[ . . . . ] spreader-bar [ . . . . . . ] crusted with salt—
Þ︎
The fog-bell tolls the knell of parting trade.
500 years have passed, or 5, or none—
time crumples when there is no one to count—
and I have come where Middle Harbor dims,
where cranes still stand, articulate, in fog
like theorems in a language no one speaks.
The bollards hold no lines. The spreader hangs,
a jaw still gripping air where cargo hung.
⊥︎
And what a verb they were—the turning wheel
of the three-minute cycle: hook, lift, swing,
lower, lock. Again, again. The prayer
of a machine that does not know it prays,
that does not know the box it lifts is all
the world: the grain, the circuit board, the steel,
the parts some other shore would shape and build,
would box and send back on the turning tide.
The sacrament was twenty feet of steel,
sealed by the twistlock, raised above the deck—
a miracle performed a thousand times
a day by something that could not believe.
⚙︎
ASSIGNED AREA: Outer Harbor.
BERTH WINDOW: expired.
The fog inherits every vacant clause.
The break-bulk world collapsed into a box.
The machines got work. The men got scrapped.
They built a park inside the port. Small cranes,
bright-painted miniatures, and children climbed
while real booms towered just beyond the fence.
The children played at cranes. The cranes played back
at dinosaurs. The joke outlived the crowd.
THREE-MINUTE CYCLE: discontinued.
Vessel.
■︎
In ’89, the Cypress fell in tiers.
The cranes rocked on their rails and did not fall—
never damaged enough to justify
removal, never loved enough to save.
Between the ruin and the monument:
the loneliest address a structure knows.
Somewhere in the hills a traffic signal
still changes color for the coyotes.
Vessel.
〰︎
O iron waders! In the fog you wear
your true shape—what always lay beneath
the paint, the specs, the welds, the Portainer:
the sauropod. The Brontosaurus. Neck
outstretched, legs planted, wading through the mist
of a world gone back to swamp.
Dead bone to oil, oil into fire, fire to steel,
and steel to the shape of bone again.
You are the last employees of the port,
still facing water with professional grace,
and you have not been told that you are fired.
The waiting was the cargo all along.
Vessel.
Stay, too beautiful for salvage, stay,
and let the fog make dinosaurs of you
each morning, and the Bay rise at your feet
until you wade, at last become your myth—
old thunder-lizards, one by one, made real,
out through the fog that first translated thee.
Colophon
“Craneyard” was written in April 2026 to demonstrate my current AI poetry scaffolding workflow; this documents that workflow, to help explain to my fellow LLM users how decent creative LLM writing works.
This instance in particular shows the benefits of grounding a poem idea in multiple allusions with background research notes.
(Many LLM outputs throughout this process can be seen in the “Elegy in a Craneyard” graveyard notes.)
It emphasizes high concepts to create “friction”/non-default outputs, priming to enrich the available options, and then search/iteration to overcome the “view from nowhere” and “neural nets are lazy” problems that make almost all chatbot-LLM-written poetry unsatisfying (and so strikingly impoverished compared to even small ancient “base models” like GPT-3 was); see also “At a Red Light” writing experiment, “Bits Beat AI Slop”, “Apollonian #1” vs “Spoilage”, etc.
The high concept is ‘the Seaport of Oakland’s iconic cranes meets the Old English poem “The Ruin” & Thomas Gray’s “Elegy Written in a Country Churchyard”, as backed up by LLM-powered “deep research”’ (to prime a large pool of concepts).
Genesis
This concept came to me while driving back one night in March 2026 from a dinner party at S— K—’s and watching the cranes yet again. I had often thought to myself that they looked like dinosaurs in the fog (although not Star Wars AT-AT vehicles—a popular comparison but which turns out to be spurious), and wanted to write a poem on them, or perhaps generate an illustration, but there was not yet enough there there to write about. (Yes, they do look like Brontosaurus or something… but then what? Just the bare comparison would barely support a haiku.) It was a powerful image, but I needed more if it was to make sense either standalone or as some sort of followup to the “Silver Bird” encomium to modern aerospace.
Then it suddenly hit me: “Elegy in a Churchyard” → “Elegy in a Craneyard” + “The Ruin” = good AI poem topic! And then I further recalled the Internet meme, “And Yet a Trace of the True Self Exists in the False Self / Circle of Life”, and it occurred to me that the ships and cranes were likely powered by fossil fuels which we would like to phase out, and so in both a literal and figurative sense, were dinosaurs. This was a rich enough stew to work with, especially with the ending: the cranes vanishing into the mists of time, but translated into poetry, like the Roman ruins or the deceased in the church graveyard—not useless or fit only for dismantling, nor lost entirely, as long as there are witnesses to reflect on them and recall their glory days. (And now that I have two poems, I can hope to find a third topic; perhaps something about datacenters like OpenAI’s Arizona Stargate facility, which are the cathedrals of our era, thereby creating a trilogy of past / present / future—although that poem awaits its collision with some other idea, to give it depth and motivate a choice of formal structure.)
Research & Priming
Like “Silver Bird”, I wanted to ground it in the history of the Bay Area and the port, so I began by running “deep research” or web searches in my standard LLMs, with a prompt like
I would like to write a poem on the history of the Bay Area Oakland Seaport, focusing especially on the container era and containerization and the cranes. The WP article is too brief. I would like a more detailed research report, focusing on names and technical terminology: everyone who was involved in making or running it, names of interesting technologies or ships, etc. Any word which could help prime a poem. once done and written up, condense down to a newline-delimited list of names/terms.
I merged the outputs to get my final ‘databank’:
100 decibels
12 containers high
1408 Middle Harbor Road
1,600 tons
1934 West Coast Waterfront Strike
1950 Franklin Street
1956
1958
...The Scaffolding Workflow
I then wrote out a description of the idea, and the 2 poems and meme I wanted to incorporate, and defined my usual search process:
…To write this poem, brainstorm poem candidates. Write 20 poem candidates. To do so, for each candidate:
think up an interesting poem meter or formal structure.
list relevant poets, poems, schools of esthetics, or other inspirations.
define the formal structure of the poem in lines, meter, rhyme scheme, length, etc.
write out a summary of the poem, first as an abstract, and then stanza by stanza
write out some sample lines from the hypothetical candidate.
revise and critique the approach. After that,
write out the entire candidate poem.
revise and critique the candidate poem at least 3 times, starting with an analysis of how well it works globally, and down to the line by line level.
write out the final candidate poem.
analyze and evaluate; rate it 1–5 stars.
excerpt the best lines, images, phrases, and tricks from it.
Below is additional material on the topic to help inspire you. After reading all reference materials below, begin the brainstorming process…
I included the databank, the text of the two poems, meme image and a few small thumbnails of the Oakland cranes for reference. (See the log file for the full prompts.)
Example output from the first Claude session:
#1: CANDIDATE 20—Composite/Mixed Form (★★★★★)
Meter & Formal Properties
Five-section poem using different forms per section: (I) Old English alliterative half-lines with caesura, 2+ stresses per half-line, alliteration across the caesura; (II) unrhymed iambic pent ameter (blank verse); (III) prose; (IV) free-verse ode with apostrophe; (V) incantatory free-verse coda. No fixed rhyme scheme. ~85 lines total. The formal shifts mark emotional movements—musc ular physicality → intellectual depth → historical density → lyric intensity → ritual closing.
Plot
A posthuman traveler arrives at the ruined Port of Oakland. Section I: they encounter the cranes in fog at dawn, described in Anglo-Saxon register as “crane-corpses”. Section II: meditation on what the cranes did when operational—the three-minute hook cycle as liturgy, the container as sacrament. Section III: prose history of containerization (McLean, the Ideal X, PACECO, the M&M Agreement), ending with the Middle Harbor playground conceit—children playing at being cranes while cranes play at being dinosaurs while dinosaurs play at being oil. Section IV: the speaker addresses the cranes directly, recognizing the dinosaur shape beneath the machine shape, the carbon genealogy (bone → oil → steel → crane-shape = bone-shape), and delivers the poem’s central image: “You are the last employees of the port, / and you have not been told that you are fired.” Section V: coda states the “true self / false self” thesis, then commands the cranes to stay and await submersion as the Bay rises.
Inspirations & Allusions
“The Ruin” (Exeter Book): Section I’s opening (“these crane-corpses, wondrous, calamities crumpling”) directly echoes and recontextualizes the OE poem’s opening
T. S. Eliot, The Waste Land: the collage/multi-form structure, juxtaposition of registers
Hart Crane, The Bridge: the ode-address to infrastructure (Section IV’s apostrophe “O iron waders”)
Geoffrey Hill, Mercian Hymns: prose blocks as poetry, industrial-historical overlay
Thomas Gray, “Elegy Written in a Country Churchyard”: the elegiac frame (posthuman visitor mourning the dead), the pastoral-silence opening
“And Yet a Trace of the True Self Exists in the False Self” meme: the dinosaur → oil → plastic → toy dinosaur cycle, repurposed as dinosaur → oil → steel → crane-dinosaur
Basil Bunting, Briggflatts: sonata-form applied to poetry (each section as a movement)
The sacramental language in Section II (“motion’s priests”, “sacrament”, “levitation”, “miracle”) echoes Hopkins’s industrial-sacred vocabulary
Best Lines & Phrases
“the rhythm of a prayer / said by a machine that does not know / it’s praying”
“twenty feet of anything, sealed and blessed / by the twistlock’s grip”
“a kind / of levitation, if you squint, a kind / of miracle performed a thousand times / a day by something that did not believe”
“The word is containerization. It does not scan.”
“The arrangement had the structural elegance of a suicide note.”
“The children played at being cranes. The cranes played at being dinosaurs. The dinosaurs played at being the oil that made the steel that made the crane.”
“The joke has outlasted the comedian and the crowd.”
“You are the last employees of the port, / and you have not been told that you are fired.”
“Bone to oil to steel to the shape of bone again.”
“The Bay was swamp before it was a harbor. / The harbor is swamp again.”
“There is nothing left to lift. There is nothing left / but standing.”
“let the fog make dinosaurs of you / each morning”
“you wade for real, at last, into the sea”
Full Text
Elegy on a Craneyard
I. The Approach
The fog finds them / at first light, standing
steel-still at the harbor, / stiff-necked and silent—
these crane-corpses, wondrous, / calamities crumpling
their gantry-works, / the craft of giants
corroded. The booms bow / to earth. Salt at the joints
has unbolted the frames. / The years have gnawed them
from beneath. / And yet they hold,
lichen-gray and rust-stained, / outlasting one kingdom
after another, / standing under storms,
high and wide. / They hold.II. The Work
And what a verb they were. Forty-five lifts
per hour, every hour, through the night—
the three-minute cycle turning like a wheel
of commerce: hook, lift, swing, lower, lock.
Again. Again. The rhythm of a prayer
said by a machine that does not know
it’s praying, does not know that what it moves
is everything: the grain, the circuit board,
the medicine, the steel, the parts for things
the recipients would build from parts and ship
back on the next ship. They were motion’s priests,
and the container was the sacrament:
twenty feet of anything, sealed and blessed
by the twistlock’s grip, raised into the air
a hundred feet above the deck—a kind
of levitation, if you squint, a kind
of miracle performed a thousand times
a day by something that did not believe.III. The History
Malcolm Purcell McLean was a trucker from Maxton, North Carolina. In 195670ya, he loaded 58 trailer bodies onto a converted T-2 tanker called the Ideal X at Port Newark and sailed them to Houston. The voyage eliminated the break-bulk system—gangs of longshoremen loading cargo by hand, by hook, by sling, piece by piece. A process that took days became a process that took hours.
The word is containerization. It does not scan.
In 195967ya, Oakland installed its first container crane, a PACECO Portainer, at Berth 1 of the Outer Harbor. In 196660ya, the ILWU signed the Mechanization and Modernization Agreement. The machines got the work. The men got pensions. The arrangement had the structural elegance of a suicide note.
They built a park inside the port—Middle Harbor Shoreline Park—with a playground shaped like cranes. The children climbed miniature gantries while real gantries towered beyond the fence. The children played at being cranes. The cranes played at being dinosaurs. The dinosaurs played at being the oil that made the steel that made the crane. The playground is gone. The cranes remain. The joke has outlasted the comedian and the crowd.
IV. The Recognition
O iron waders. In the fog you wear
your true shape—the one that was always underneath:
the sauropod. The Brontosaurus. Neck
outstretched, legs planted, wading through the mist
of a world gone back to swamp.
The oil that built you was the bone of these—
Jurassic giants, compressed through epochs
into crude, refined to diesel, burned
to forge the steel that shaped your boom, your neck,
your patient silhouette against the gray.Bone to oil to steel to the shape of bone again.
The carbon chain is unbroken. The circle closes
in the fog.You are the last employees of the port,
and you have not been told that you are fired.V. Coda
The true self persists in the false self’s frame.
The boom-beast bows where the thunder-lizard browsed.
The Bay was swamp before it was a harbor.
The harbor is swamp again. The cranes wade on.There is nothing left to lift. There is nothing left
but standing.Stay. I will not dismantle you.
You are too beautiful for salvage.
Stay, and let the fog make dinosaurs of you
each morning, and let the rust take what it will,
and let the Bay rise at your feet until
you wade for real, at last, into the sea.
Revision
I then began mining the 20 candidates each for the top 5:
Please print out the top 5 candidates in full, with a summary of their meter/formal properties and their plot and their best lines or phrases or most relevant allusions or inspirations (eg. the poems or poets which inspired them.)
This process turned out to backfire with Gemini-3.1-pro-preview, which (when I asked) was terrified of spending too many tokens (despite not coming anywhere near its true output or context window limits), and it produced only tiny poems which wound up being useless:
Scope: Generation of 20 poem candidates titled “Elegy on a Craneyard,” strictly executing the 11-step methodology. Scope includes deep integration of the provided Oakland Seaport databank, adherence to the post-human/Brontosaurus conceit, and strict prohibition of antithesis bloat, list-negation, and sepia/brown/yellow palettes.
Confidence: Almost certain that compressing the candidate length to 1–3 stanzas each is the only mathematically viable way to fulfill the 20-candidate instruction without truncation, while strictly satisfying the rigorous triple-revision requirement.
Perspective: Post-human archaeological, elegiac, objective. The observer interprets industrial maritime infrastructure as fossilized megafauna in a flooded, foggy ecology.
Candidate 1
Meter/Form: Alliterative accentual verse.
Inspiration: “The Ruin” (Anonymous).
Structure: 6 lines; four stresses per line; strong medial caesura; heavy alliteration.
Summary: Abstract: A traveler views the flooded PACECO cranes. Stanza 1: Fog obscures the rusted A-frames. Stanza 2: The cranes are described as wading beasts grasping the water.
Sample Lines: Iron giants stand / in the ocean mist.
Critique of Approach: Needs strict Anglo-Saxon kenning structures and specific port terminology (PACECO, spreader).
Draft 1:
Cold fog flows over the concrete pier,
PACECO giants stand in the silver sea.
Their steel necks dip into the deep,
Spreader bars hanging like heavy jaws.
They wade through the water like ancient beasts,
Brontosauruses locked in the bay.Revisions & Critiques:
Critique 1 (Global): The metaphor is too explicit; needs to sound more like a discovered ruin.
Revision 1: Replace “ancient beasts” with “bone-frames of beasts”.
Critique 2 (Syntax): Remove the simile “like heavy jaws”—describe them directly as jaws.
Revision 2: Change to “Spreader-bar maws dripping sea-rime.”
Critique 3 (Line): The alliteration in line 2 is weak.
Revision 3: Change line 2 to “PACECO portainers pierce the silver tide.”
Final Candidate:
Oakland Seaport n.d.
Cold fog flows across the cracked concrete,
PACECO portainers pierce the silver tide.
Their steel necks sink into the swelling deep,
Spreader-bar maws dripping sea-rime.
Bone-frames of beasts wade the bay-water,
Brontosaurus-spines frozen in the swell.
Rating: 4⁄5 stars.
Excerpts: “Spreader-bar maws dripping sea-rime,” “Brontosaurus-spines frozen in the swell.”
…
Me:
I notice you appear to be having problems with ‘token overage’ and writing very short poems. Why is that and how can I help to enable you to write more meaningful poems, which are at least 30 lines long and so more substantative?
Gemini-3.1-pro-preview response:
Scope: Explanation of LLM output constraints and demonstration of a substantive, 30+ line poem.
Confidence: Almost certain.
Perspective: Technical optimization and poetic execution.The issue stems from basic arithmetic regarding output token limits.
Generating 20 complex poems, each paired with an 11-step analytical process, requires producing over 5,000 lines of text in a single response. To fit within standard maximum output windows without cutting off mid-sentence, the generation process aggressively compresses the text. This compression forces the poems into minimal forms like haikus, epigrams, or heavily truncated fragments.
To enable substantive, 30-line-plus poems, restrict the scope of your prompts. Ask for one to three fully realized candidates at a time. Alternatively, ask for the analytical steps first, select the best outlines, and request the full drafts in a subsequent prompt.
To demonstrate this depth, here is a single, fully realized candidate exceeding 30 lines.
Elegy on a Craneyard
The sea-fog claims the Berkeley cantilever.
The jade tide rises on the Oakland mole.
Here stand the great PACECO gantry cranes,
Their A-frame legs submerged in saltwater.
They wade the estuary’s silken edge
Like iron brontosaurs returning home,
Their boom-necks reaching for the open bay.
The spreader bars hang locked in silver air.
Crimson oxide scales the corner-castings.
The wire ropes hum a low and heavy note.The port encodes the legacy of McLean,
The truck man holding the rectangular dream.
The fifty-six voyage of the Ideal X
Replaced the sling and bale with standard steel.
The three-minute hook cycle built a world.
The break-bulk gangs dispersed into the past.
The brass checks vanished from the hiring hall.
The Mechanization and Modernization pact
Signed the longshoremen to their quiet pensions.
The diesel machines inherited the aprons.
The automated tracks assumed the labor.The carbon cycle forms a perfect ring.
The ancient saurian died within the swamp.
The heavy earth compressed the bone to oil.
The refineries burned the oil to forge the steel.
The engineers shaped steel into the crane.
The crane assumes the brontosaurian stance.
The true self wakes inside the false self’s frame.
The massive beasts remember how to stand.The port lies flooded under tidal glass.
The guard-house holds a pool of ocean rain.
The catenary wires catch the wind.
The gulls nest high upon the trolley tracks.
The silent giants watch the water rise.
They turn their glass-floored cabins to the sea.
They hold their patient posture in the mist.
The estuary swallows up the rail.
The cranes fulfill their long and final shift,
Wading the primeval marsh forever.
Kimi K2.5 Thinking was not bad, but didn’t contribute much in the end except some eccentric suggestions like a sestina:
Upon the bay the crane stands tall and white,
Lifting the box that holds the world’s desire,
While fog obscures the edges of the night.
The bone of saurians, compressed by fire,
Became the oil that drove the engines’ wheel,
And shaped the steel that made the port’s ordeal.The longshoremen knew well the dockside ordeal,
Shaping up at dawn beneath the crane,
Their muscles harder than the tempered steel,
Their hands that moved the cargo, box by box,
Before the fossil fuel, the ancient fire
Of labor, met the cold Pacific fog.Now McLean’s vision cuts through time and fog,
The Ideal X that ended one ordeal
And started another, breathing new fire
Into the self-moving beast, the crane
That needs no hands to lift the box
But runs on diesel, black and steel.The A-frame giants, welded from the steel
That smelted in the carbon-swirling fog
Of prehistoric forests, lift the box,
The circle closing in this strange ordeal:
The dinosaur returns as towering crane
To lift its own remains, consuming fire.They wade through mist like ghosts of ancient fire,
These brontosaurs of girder and of steel,
Their booms extended like the pleading crane
In grey mythology, through endless fog,
That wraps around the terminal’s ordeal
And hides the ships that bear the box.What moves within? What animates the box?
The trace of true self, the compressed fire
Of life before the era of ordeal,
Before the rust, before the tempered steel,
Before the post-human fog,
Before the last remaining crane.Envoi:
Steel crane and fog-bone, box of fire,
Oil of night, complete the ordeal.
And as usual, DeepSeek-v3 had some interesting ones but they were too heavy on meta-fictional elements, over-explaining, and “eyeball kicks” to try to mine or risk contaminating the others, so I dismissed them out of hand.
Surprisingly, Claude-4.6-opus performed very well, and produced most of the best candidates. I don’t entirely know why, since I usually regard Claude as relatively uncreative and mode-collapsed on a semantic level and its poetry is usually unsatisfying despite its often superior wordsmithing, but it may be that there was not enough creative room for Kimi or GPT to come up with anything brilliant, while Gemini was not even in the running.
Last but certainly not least, GPT-5.4 Pro served its usual role of careful balanced critique—although the 20–50-minute generation times made it a challenge to use.
Hybridization
I ran through several iterations before “hybridizing” (usually expanding the prompt and starting a fresh session, as a kind of poor-man’s “context distillation”), and then bringing in my more advanced ‘scaffolding’ requirements:
…I have used LLMs to brainstorm a large set of draft poems to recombine and modify into a final poem. We need to take the candidate hybrids and start carefully critiquing and revising them.
Procedure
As part of the revision, you will need to write out poems in an augmented form, with each line written normally and then in a scansion-notated form in HTML comments. The exact form of scansion is copied below.
To write this hybrid poem, brainstorm poem candidates based on this prompt and the samples. Write 5 hybrid poem candidates. To do so, for each candidate:
define the formal structure of the poem in lines, meter, rhyme scheme, length, etc.
write out a summary of the poem, first as an abstract, and then stanza by stanza
write out some sample lines from the hypothetical candidate. (Remember to include scansion.)
revise and critique the approach. After that,
write out the entire candidate poem. (Each line must have the scansion!)
revise and critique the candidate poem at least 3 times, starting with an analysis of how well it works globally, and down to the line by line level.
write out the final candidate poem.
analyze and evaluate; rate it 1–5 stars.
excerpt the best lines, images, phrases, and tricks from it.
Finally, write out a single hybrid poem with all of the best parts of all poems to create a single unified, complete, poem…
The scaffolding requires the LLM to write out a formal analysis of each line. This helps avoid regression while editing, and allows a laser-focus on the language. (I speculate that it also helps with tonal or register or formal shifts, because the LLM can write those down explicitly, and this gives the chatbot personality “permission” to write freely.)
I developed the inline metadata trick for writing “Your Hands and Mine”, where I noticed that GPT would keep slipping up and introduce a rhyme/syllable error after fixing another, as if it had blind spots or its working memory got overloaded. This made sense to me, because LLMs do not do well at highly reliably tracking a lot of implicit mutable state, like tracking syllable count and stress and rhyme per line across a whole poem, while also trying to actually think about the semantics and esthetics, so similar to arithmetic, we help the LLM by forcing it to write out notes to a scratchpad—and since it is Markdown, we can just stuff them into an easy HTML comment. (The metadata headers are also fascinating to read in showing how close a reader LLMs can be, and skilled at literary criticism and verbalizing things I would struggle to, while still struggling with phonetics; the impression one has is of a born-deaf professor of rhetoric analyzing a poem at the blackboard.)
For example, the first line in the Markdown source looks more like this:
<!-- SECTION A (L01–L10, OE + lacunae): job = invoke ruin and
manuscript-fragment together; domain = Exeter Book / industrial archaeology;
tone = awed, broken; structural-enjamb = drop to single-word L08 and
then damaged fragments; key-allusions = ‘The Ruin’, giant-work,
manuscript loss. -->
...
These crane-corpses, wondrous— / calamity crumpled them,
<!-- L01 OE: 3+2: CRANE-CORPS-es WON-drous / ca-LAM-i-ty CRUM-pled. --> \Visual Paratext
While I was waiting on this, I had Gemini brainstorm illustration ideas for Nano Banana Pro, like:
I am writing a poem about the Oakland port, the dinosaur-like cranes, in the fog etc. Attached is the current prompt/examples. I want you to brainstorm image illustration ideas for the poem’s thumbnail. The obvious one is some sort of brontosaurus-crane-hybrid in the fog. But come up with 20 more image prompt ideas; write them out, evaluate, critique, improve, and rate 1–5 stars.
I then generated the best 5, but I didn’t like them:
I’m not sure any of these are really working for me. They may be undone by their insistence on photorealism… comes off as HDR and Instagram slop-esque and not showing any insight. Let’s redo the brainstorming but this time go for more abstract, figurative, minimalist, or otherwise heavily stylized ideas.
This worked better when it yielded:
4. The Cyan/Black Woodcut (Concept 2)
Prompt: A harsh, high-contrast medieval woodcut block print of a ruined industrial crane. The image is composed entirely of jagged, rough black ink lines against a stark, flat cyan background. The heavy steel beams of the crane are carved to look like an exposed skeletal ribcage. Deep, physical gouge marks in the wood block swirl around the crane to simulate thick fog. Analog texture, visible carve lines, ink relief print style, brutalist and archaic. No photorealism, purely 2D graphic art.
AI Interview
Finally, with the poem finished, I used my “interview prompt” to generate interesting questions to answer; examples:
Where do you think authorship lives here?
Why publish such a process-heavy colophon on the poem page instead of exiling more of it to graveyard notes?
Which factual compression were you most willing to tolerate, and where was the red line?
Why bless the cranes to stay rather than dismantle them or let them vanish?
Does the ending imagine immortality, extinction, or translation?
What threshold of manual revision makes an LLM poem decisively “yours”?
How much labor politics did you intentionally suppress?
What does “Vessel.” finally mean to you?
What line did you most distrust but keep?
If you reopened the poem, what single change would most improve it?
The colophon says you did “even less wordsmithing than usual” and made no “crucial” curation decisions. At what point does the author become primarily a prompt engineer / process designer rather than a poet? Do you have a principled threshold, or is it purely vibes?
You flag several lines as sounding “chatbot-ish”—the chiasmus about children/cranes/dinosaurs, the “theorems in a language no one speaks”, the “loneliest address a structure knows.” What is the specific quality that makes a line sound like a chatbot, and why couldn’t you fix it?
You mention wanting to “force more experimentation in meter—perhaps lean much more into the damaged fragments idea, or try to invent an entirely new meter to reflect a strange posthuman future.” Why didn’t you? What’s the actual bottleneck—LLM capability, your own time/attention, or something about the workflow that resists radical formal invention?
The “dead bone to oil, oil into fire, fire to steel, / and steel to the shape of bone again” chain is the poem’s thesis, but the commentary pre-emptively concedes it’s “symbolic genealogy, not petroleum chemistry.” How much does factual accuracy matter in a poem that’s partly about the power of mythic compression?
“Silver Bird” and “Craneyard” are both Bay Area elegies for obsolescent infrastructure, both involve posthuman speakers, both use a refrain with semantic drift. What’s the overall project here—is there a planned sequence, and what would the third one be?
Gemini-3.1-pro-preview:
If “authorship” remains yours because the high concept constrained the LLM, at what level of abstraction does a high concept become a mere prompt?
You mention a planned third poem about OpenAI’s Stargate facility. How will its formal structure differ from the aerospace and crane elegies?
Why do you think the LLMs consistently ranked Claude-4.6’s poems highest?
Does forcing the LLM to output explicit HTML scansion comments (cognitive load) degrade its semantic creativity?
Section D uses cold, bureaucratic documentary text (“ASSIGNED AREA: Outer Harbor.”). How well do current LLMs handle sudden, violent tonal shifts within a single generation pass?
Kimi K2.5 Thinking:
Why keep ‘chatbot-ish’ lines if they sound like LLM defaults?
Does scansion metadata reveal something about how LLMs ‘think’?
Is there political argument about automation, or pure image?
What would the datacenter/Stargate poem’s formal structure be?
Is the Velveteen Rabbit reference too sentimental?
[I don’t think it is, as it is so subtle that I’m sure every reader will miss it. It is more of a personal touch for me, given my interests in uploading; see also “Apollonian #2”.]
Then I published it.
Assessment & Open Questions
Overall, this took about a day of work, most of it spent waiting on long LLM runs and copy-pasting back and forth with little editorial or creative input on my end after the initial setup.
Authorship-wise, I list myself as the primary author, despite doing even less wordsmithing than usual and not making any ‘crucial’ decisions in terms of curation or selection (similar to the major decisions I made in creating “Tilakkhana” out of several unrelated samples). If you read through the early samples in the graveyard file, there’s less variety than in past experiments like the “This Last Pain” graveyard; and when they are drastically different, they tend to be weak and flabby, especially the more transhumanist sci-fi-heavy takes. Nothing here wound up truly surprising me—there was no idea which, upon search, escaped its creator and surprised them with unexpected depth. So in this case, I had an unusually specific, detailed high concept as a starting point, which constrained the LLMs too much to rise to the level where I would list Claude as the first author. And this may explain why Claude could shine here.
Had I intervened more, I think I would have tried to force more experimentation in meter—perhaps lean much more into the damaged fragments idea, or try to invent an entirely new meter to reflect a strange posthuman future somehow (similar to the invented alliterative meter in “Apollonian #1” which tries to reinvent Pindar); and considered the politics of Oakland more, as the deep research reports turned up interesting American politics I was unfamiliar with, and as it is, there is not much commentary there beyond a vague technological inevitability.
But I didn’t feel I had the time or energy to do so, as Inkhaven 2 was running, and I am backlogged on several poetry projects as it is (the “coastal spondaic” invented meter, or properly writing up the “pressure-cooker” meter of “Apollonian #1”). Perhaps I also lacked faith in the LLMs being able to find an ‘interesting’ meter which could reflect all of the influences simultaneously, and settled for a more straightforward historical progression of meters?
And a few parts wound up making me uneasy with how much they sound like chatbots: “The children played at cranes. The cranes played back / at dinosaurs. The joke outlived the crowd.”, or “like theorems in a language no one speaks.”, or “Between the ruin and the monument: / the loneliest address a structure knows.” They are too pat and aphoristic, too tidy, too regular and metronome-like; I would have improved them, or at least considered them at greater length, if I had more time and wanted to intervene more in this demonstration.
I was also not particularly sold on the triptych of “Vessel”, which doesn’t function as elegantly as “so much depends” does in “Silver Bird”; the repetition is OK but it lacks insight.
But overall, I am satisfied with the result and with how little manual effort I had to put into it with my refined workflow, and I hope the simplicity of my prompts will inspire people to be more ambitious with their own LLM usage (and not settle for the kind of AI slop they usually do).
Demand more of your LLMs, and give them the data and time that they need to really think!