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
Works on evals at Prime Intellect and on open-model coverage at Interconnects [Reported: X profile x.com/xeophon]. GitHub 'xeophon' (linked from his site) has 100+ commits in PrimeIntellect-ai/verifiers through 2026-09-23 [Verified]. Co-writes the Interconnects 'Artifacts Log' open-model recaps with Nathan Lambert and is described there as a PhD student at Trier University [Reported: interconnects.ai].
- X profile: x.com/xeophon
- GitHub: github.com/xeophon
- Site: florianbrand.com
- Blog: interconnects.ai/t/artifacts-log
Public work
- verifiers (contributions) repo MIT last activity 2026-09-23 · 4,650 GitHub stars on 2026-09-24
Prime Intellect's library for RL environments and evals; his recent commits gate tool calls at the response boundary, add sandboxed MCP servers, Harbor solver/verifier image overrides, and network-policy mediation [Verified]
- Interconnects Artifacts Log newsletter no license stated last activity 2026-09
Monthly recaps of open-weight model releases, co-authored [Reported]
- beam repo MIT last activity 2026-02-22 · 16 GitHub stars on 2026-09-24
Skill that moves a live coding-CLI session (codex, pi, claude, amp, opencode, kimi) plus transcripts and auth to a remote Prime pod so it can resume there [Verified]
- bibtex-mcp repo MIT last activity 2025-07-25 · 11 GitHub stars on 2026-09-24
MCP server searching arXiv, DBLP, Semantic Scholar and OpenAlex concurrently and returning BibTeX; hosted SSE endpoint or local stdio [Verified]
- Interconnects podcast: 'Open models: Hot or Not' podcast no license stated last activity 2025-12-18
Discussion of open-model releases [Reported]
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
5 of 5 lenses: evals, agents, mcp, local-models, research-method
verifiers is an MIT eval/environment library he actively maintains; skill and agent checks can run through it, and harnesses can be benchmarked against it. The Artifacts Log is a curated monthly feed for choosing local MLX models. bibtex-mcp fits franken-research citation work.
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
- verifiers: environment + rubric API and the tool-call gating commit (github.com/PrimeIntellect-ai/verifiers/commit/1784f111334c83b880e0d2d1c8b0e1282a689496). Candidate standard harness for evaluating agents and skills Effort: medium.
- Artifacts Log monthly (interconnects.ai/t/artifacts-log). A curated monthly source for open-model releases Effort: small.
- bibtex-mcp run locally (github.com/xeophon/bibtex-mcp). Citation lookup for franken-research assessments Effort: small.
Before reusing anything: verifiers, beam and bibtex-mcp are MIT. beam's README documents that it copies local CLI credential files to the remote pod by default, with a --skip-auth flag to turn that off. Some Artifacts Log posts are paywalled. florianbrand.com failed TLS verification from here.
Sources
- x.com/xeophon
- github.com/xeophon
- github.com/PrimeIntellect-ai/verifiers/commit/1784f111334c83b880e0d2d1c8b0e1282a689496
- github.com/PrimeIntellect-ai/verifiers/commit/3085a25421d1f3d0f27f7abeaceebf7c97025de1
- github.com/xeophon/beam
- github.com/xeophon/bibtex-mcp
- interconnects.ai/t/artifacts-log
- interconnects.ai/p/open-artifacts-in-january-6-reasoning
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 70 of people.jsonl.
Limits
Not verified: florianbrand.com could not be read (certificate error), so the PhD and research statements rest on Interconnects and search snippets.
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.