← The Independent 100: a study

Minh Nhat Nguyen

#59 in The Basement Labs, the curator’s rank and section @menhguin 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

[Verified] AI researcher, first author of the min-p sampling paper (ICLR 2025, arxiv.org/abs/2407.01082). Previously at HUD (agent environments and evals) [Reported: X profile x.com/menhguin].

Public work

  • Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs paper no license stated last activity 2025

    Dynamic truncation sampler scaled by the top token's probability. The ICLR orals page reports adoption by Hugging Face and vLLM.

  • minp_paper repo MIT last activity 2025-08-13 · 52 GitHub stars on 2026-09-24

    Code, evaluations and documentation for min-p.

  • moneybench_pt1_planning repo no license file last activity 2025-07-17 · 4 GitHub stars on 2026-09-24

    Planning for a benchmark of agents earning money in the real economy [Inference from the name and his GitHub profile].

  • twin-agent-seed repo no license file last activity 2026-06-09 · 0 GitHub stars on 2026-09-24

    A structure-only 'twin agent' seed cloned from his personal agent setup with personal content removed.

  • semantic-attention repo no license file last activity 2025-01-30 · 0 GitHub stars on 2026-09-24

    Initial implementation of semantic attention for long-context interpretable MoEs.

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: evals, local-models, research-method, agents

[Verified] min-p is a sampler that already ships in common inference stacks, so it is useful context for tuning local MLX models. [Reported] A published critique (arxiv.org/abs/2506.13681) finds no general quality or diversity gain, so treat min-p as a knob to A/B test, not a known win. His agentic-eval background (HUD) and twin-agent seed are close to our eval and agent-memory lanes, but the adoptable code is small.

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. Min-p paper together with its critical analysis (arxiv.org/abs/2506.13681). A worked example of a widely adopted claim being re-audited. Good material for franken-research's evidence-grading rulebook, and it settles whether min-p is worth setting in local model configs. Effort: small.
  2. twin-agent-seed structure (github.com/menhguin/twin-agent-seed). A personal-agent scaffold, to compare with other persona and agent-memory designs. Effort: small.

Before reusing anything: minp_paper is MIT. twin-agent-seed, moneybench and semantic-attention have no license [Inference: all rights reserved].

Sources

Overall confidence in this record: Medium. Sources were read on 2026-09-24 and every link was checked on 2026-09-25. The full record is line 59 of people.jsonl.

Limits

Not verified: What 'programmable LLMs' refers to: no public repo or post found. The contents of moneybench (the repo was not read).

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