Research
Two shelves. Essays are written by Romello Goodman, one per question the studio has chased. Lab notes are the experiments behind them, run and written up by Claude models under direction, filed under the model they produced.
Essays
A month after the first model, I've trained ~60 and released 11, each starting from a question. These models are knowledge-light and shaped like their data, too small to chat with. The long-term bet is inventing harnesses that turn each one into an instrument.
Lab notes
pona-nanogpt
Three 2.7M-param GPTs trained on 6.9M characters of Toki Pona and scored sentence-by-sentence by the community's grammar checker: the word-tokenized arms clear the span-thesis null, and the released chat model writes more grammatically than its own corpus (96.9% vs 96.0%). Mixing 4.6% oracle-filtered synthetic dialogue into the same recipe turns it into something you can talk to — 160/160 grammatical replies at temperature 0.8.
studio
Three thousand fonts generated from Knuth's own Computer Modern source cover no more of real type design than five hundred did — the ceiling is set by the program, not by the sample count. A third to a half of independently-set parameter combinations won't compile at all, and one boolean, the single-storey g, is worth more coverage than every continuous dial combined.
The studio's small models are instruments — single-purpose, played rather than prompted — and sup, the studio CLI, is the accessibility argument: one greeting downloads a release and streams its voice to stdout. A handle that simple works in a shell pipe, which means it works for another model.
The studio writes to a rulebook — twelve editing operations encoded as a skill, distilled from Anthropic's research posts, Thoughtful Lab, and Ramp Labs, piloted on two files and then swept across the studio: nine model cards, ten docs, and the website's visitor copy, 130-odd edits in all. The pilot's diagnosis held at scale — the studio's biggest tic was emphasis overload, and the sweep removed bolded lines over reintroducing them at roughly four to one.
A single afternoon spent improving all four sup computer models at once — a larger model planned a per-model optimization, small runs executed it. Two new releases (shakespeare-nanogpt-3, kenosha-kid-nanogpt-2), one migration, one eval-only characterization, and a handful of findings that only show up when you look across projects side by side.
glyph-nanogpt
A round-2 training plan built from a type-design chapter makes three predictions a model run would bet on — so all three were measured first, with zero training. One died (the chapter's craft axes explain 2.1% of what the generalist finds hard; outline complexity explains 17.9%), one passed (quantization binarized overshoot instead of erasing it), and one survived after the corpus corrected the plan itself (u is a round letter, whatever the shape grouping says).
Twenty-six 1.8M-param GPTs, one per lowercase letter, against one letter-conditioned generalist at two sizes — all trained on 82k glyph outlines from 759 open-licensed sans-serifs. The 47.8M generalist wins mean bits-per-char by 2% but fails to draw a well-formed glyph 29% of the time where the specialists fail 8% — and it ships anyway, on purpose: the studio releases one evolving instrument, with the case's numbers frozen as the yardstick every future version has to overtake.
linewell
The shakespeare model's own likelihood is register-blind: fluent Gutenberg editorial prose scores inside any NLL band that admits verse, and the model's most inevitable text is the junk — footnotes, [Illustration] tags, speaker lists at 1.2–1.8 NLL — so the band's raised floor, not its ceiling, is the load-bearing edge. An LLM judge riding the same steer layer held verse register where the band drifted into publication history.
token-chess
Five rounds of Token Chess — a benchmark where LLMs may not author chess moves, only steer Daydream's sampler under a token budget — asked what a token actually buys. Round one: plies, at a worsening rate (every game forfeits; legality collapses 49% → 14% out of the opening book). Round two: remove death and nothing discriminates. Round three: price batches and candidate-picking with engine adjudication, and the benchmark finally separates players — then ministral, the worst sampler on the board, beats olmo 3–1 on pure tempo. Rounds four and five close on memory: assigned a free notepad, olmo writes zero notes in 24 games; offered the choice, it picks the notepad 24 seats out of 24, explains why every time, and still writes nothing.
daydream-chess-nanogpt
A three-tier chess-move GPT family (5x5, 8x8, and a custom 12x10 board) built around a single inversion: illegal moves are rendered as dim near-misses instead of being masked away by the sampler. All three tiers land in a tight band of legal-move rate (35-39% on a raw, unresampled first try) despite very different board sizes, vocabularies, and corpus sources -- and two separate facts in the original design plan turned out to be wrong when checked against the live engine instead of trusted from web research.
core
A repo-wide audit by a larger model found the small-model studio's engine had two advertised code paths that crashed on use, a metric that quietly flattered char models, and a resume that restarted. The fix that outlasts the fixes: a twenty-second smoke test that trains a real (tiny) GPT from scratch on every push — train, resume, sample, eval, export, parity — so the wiring can never silently rot again.
gatsby-nanogpt
gatsby's first corpus cost ~$6 of Claude API to write. This round throws that out and has a mixture of four local open models — Olmo, Ministral, Gemma, Granite — write the corpus instead: free, unlimited, and in four different voices. The model that results matches the paid baseline's behaviour at $0. The catch, and the finding: the blend is a designed object. A granite-heavy first round broke the green-light dial; rebalancing off it and doubling the data brought the dial back.
A char-level model built to compulsively reach for Gatsby's green light — and the $0, fully-controlled ablation that found the dial's real bottleneck: signal loudness, not corpus shape.
kenosha-kid-nanogpt
The smallest obsession in the studio: a char-level model whose entire corpus is punctuated permutations of six words. A bot enumerates that space exactly; a learned model can't — and the blur it produces instead is the artifact. The finding: dreaminess is governed by two knobs, training progress and sampling temperature.
player
Don't serve a model — export only its forward pass as a static ONNX graph (tokens in, last-position logits out) and keep the autoregressive loop, sampling, and tokenization in JS, so a small model becomes a static asset that runs client-side with no server.
shakespeare-nanogpt
An LLM-assisted experiment: four rounds took held-out BPC from 2.395 to 1.919. More data was the win; regularization was the dead end.