← The Independent 100: a study

John David Pressman

#71 in The Basement Labs, the curator’s rank and section @jd_pressman Relevance to our work: 3 of 5

Bracketed tags are evidence labels: [Verified] means we read the page, file or API response ourselves, [Reported] means a source says so and we did not check the underlying thing, and [Inference] is our own reasoning.

Credit

The Independent 100 list was curated by dan (@irl_danB) and published on 2026-09-24 at independent.prose.md (announcement). The ranks and section names are his, and number 100 is his open wild-card slot. This study is ours and is not endorsed by him or by anyone on the list.

What they publicly do

Homepage: writes essays and programs; recent programs are AI-related, such as the RetroInstruct synthetic dataset [Verified: jdpressman.com]. Built MiniHF (local-model inference, preference collection and fine-tuning with the Weave MCTS sampler) and weave-agent [Verified]. He states that his X posts are public domain under CC0 [Reported: X profile x.com/jd_pressman].

Public work

  • minihf (incl. weave-agent) repo Apache-2.0 last activity 2025-11-06 · 183 GitHub stars on 2026-09-24

    Branching inference UI, preference-data collection, Weave MCTS rejection sampling, generator and evaluator LoRA tuning, RLAIF; agent/ holds weave-agent [Verified]

  • Weave Agent DevLogs blog no license stated last activity 2025-03-24

    Design log for an agent whose actions are Python blocks appended to a long program; argues agency is mostly a data problem and treats the agent as a trace generator [Verified]

  • The RetroInstruct Guide To Synthetic Text Data blog no license stated last activity 2024-07-13

    Methods for building synthetic training data [Verified: title on homepage]

  • RetroInstruct dataset Apache-2.0 last activity 2025-10-08 · 34 GitHub stars on 2026-09-24

    Synthetic data from templating, few-shot prompting and transforms of public-domain text [Verified]

  • miniloom / miniloom-sessions dataset CC0-1.0 last activity 2025-12-18 · 10 GitHub stars on 2026-09-24

    Loom (branching) UI and public-domain loom traces [Verified]

Licenses of GitHub repositories are from the authenticated GitHub license API on 2026-09-25, one row per repository in evidence/licenses.jsonl (“no license file” means the API found none; “license file present, not recognised by GitHub” means GitHub could not classify it). Other licenses are as the source states. Check the license file before reusing anything.

Relevance to our work

3 of 5 lenses: agents, training, evals, research-method

weave-agent's trace-as-data view and evaluator-guided sampling are useful ideas for turning agent sessions into eval and training data. The code is research-grade and has not been pushed since late 2025, so it is for study, not adoption.

Scored 0 to 5 against the study’s relevance rubric: 5 means public, openly licensed work squarely in our lanes that we could study or adopt now, and 1 means little connection to our work. The score is one reviewer’s judgement of how much this public work bears on our own work. It is not a ranking of people and says nothing about the person or the quality of their work.

What we would study next

  1. Weave Agent DevLog #3 and #4 (minihf.com/posts/2025-02-08-weave-agent-dev-log-4-the-spark-of-life). How he bootstraps usable agent traces; compare with how cass and ee store sessions Effort: small.
  2. RetroInstruct guide (minihf.com/posts/2024-07-13-the-retroinstruct-guide-to-synthetic-text-data). Methods for generating synthetic eval cases for agent skills Effort: medium.

Before reusing anything: minihf, RetroInstruct and miniloom are Apache-2.0; miniloom-sessions is CC0. simulacra-aesthetic-captions has no license file.

Sources

Overall confidence in this record: High. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 71 of people.jsonl.

Limits

Not verified: What he is building now: his last 20 X posts (2026-09-12 to 09-24) are commentary with no project links, and no repo has been pushed since 2025-12.

This record comes from a first-pass survey of public material by an AI agent session on 2026-09-24, edited for publication on 2026-09-25. Nothing was installed or run for it. Roles, stars and licenses change; see the study’s limits.

Request a correction

Is something about this record wrong or out of date, or would you rather not be covered? Open a correction (a GitHub issue form with this page’s address filled in). A request to remove a record is honoured without argument; accepted corrections are recorded in the changelog with the date.

Help fix it

Each opens a GitHub issue form with this page’s address filled in. You need a GitHub account.

Made by Joshua Nowak (ZestStream) with AI coding agents. Not affiliated with or funded by Jeffrey Emanuel; Joshua uses his public tools and is a paying subscriber to jeffreys-skills.md.

Source on GitHub MIT licensed