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’.
A posthuman traveler finds the container cranes of the Port of Oakland still standing centuries hence, reflecting on their work, history, and abandonment. The cranes’ silhouettes in fog resemble Brontosauruses; 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.
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—
The fog-bell tolls the knell of parting trade.
Five hundred years have passed, or five, or none—
time crumbles 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 eighty-nine, 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. (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 original concept was the Seaport of Oakland’s iconic cranes meets the Old English poem “The Ruin” & Thomas Gray’s “Elegy Written in a Country Churchyard”, backed up by LLM-powered “deep research” to prime a large pool of concepts.
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—which turns out to be a popular comparison but sadly 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.) 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, really were dinosaurs. This was a rich enough stew to work with.
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’.
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.
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 was terrified of spending too many tokens (despite not coming anywhere near its hyperparameter limits), and it produced only tiny poems which wound up being useless. Surprisingly, Claude-4.6-opus performed very well, and produced most of the best candidates. (And as usual, DeepSeek 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.) 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.
I ran through several iterations before “hybridizing”, 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 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.
For example, the first line in the Markdown source looks more like this:
These crane-corpses, wondrous— / calamity crumpled them,
<!-- L01 OE: 3+2: CRANE-CORPS-es WON-drous / ca-LAM-i-ty CRUM-pled. --> \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.
Once I had a final hybrid poem from each LLM, I had Claude choose the best one to work with, because it seemed like all the LLMs consistently ranked its poems highest on average.
Only at this point did I begin reading the poem in earnest and making manual edits. (Primarily, adding reference hyperlinks and adding metadata commentary.)
After a first manual pass to acquaint myself with it, I then ran the Poetry magazine prompt to refine it.
This yielded only a handful of edits before I declared it done, checked it all against the Manual of Style, wrote this Colophon, and published it.