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
Pseudonymous account that publishes small personal tools on GitHub under the handle [Verified: github.com/yacineMTB].
- X profile: x.com/yacineMTB
- GitHub: github.com/yacineMTB
Public work
- dingllm.nvim repo Apache-2.0 last activity 2024-10-24 · 851 GitHub stars on 2026-09-24
Minimal Lua scripts that stream LLM completions into Neovim buffers.
- dingcad repo no license file last activity 2026-01-20 · 504 GitHub stars on 2026-09-24
Live-reload CAD scripting: save a script and the renderer updates, instead of a GUI.
- talk repo no license file last activity 2023-10-17 · 586 GitHub stars on 2026-09-24
Early local voice-assistant pipeline (speech to LLM to speech).
- just-large-models repo Apache-2.0 last activity 2023-09-06 · 44 GitHub stars on 2026-09-24
Hackable LLM code with little abstraction, written for their own use.
- dingvid repo no license file last activity 2026-06-25 · 1 GitHub stars on 2026-09-24
Video editing tools.
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
2 of 5 lenses: agents, content, writing
[Verified] Most of their public output is commentary on models and RL on X. Their most-starred code (dingllm.nvim) has not been pushed since 2024-10. [Verified] Recent posts argue for building your own AI tools and training your own models, favor functional tests over unit tests, and ask about a code-smells RL environment (x.com/yacineMTB/status/2102714129890852949, x.com/yacineMTB/status/2102765846862942557). That is useful market sense, but there is little we can adopt.
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
- dingllm.nvim source: the smallest possible streaming editor-LLM bridge (github.com/yacineMTB/dingllm.nvim). A reference for the minimum viable streaming bridge between an editor and an LLM. Effort: small.
Before reusing anything: dingllm.nvim and just-large-models are Apache-2.0. dingcad, talk and dingvid have no license file per the GitHub license API (2026-09-25), which means all rights are reserved by default [Inference]. Do not copy from them.
Sources
- github.com/yacineMTB
- api.github.com/repos/yacineMTB/dingllm.nvim
- api.github.com/repos/yacineMTB/dingcad
- x.com/yacineMTB/status/2103114444037374063
- x.com/yacineMTB/status/2102714129890852949
- x.com/yacineMTB/status/2102765846862942557
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 53 of people.jsonl.
Limits
Not verified: Whether dingboard is still active. What RL or robotics work the account is doing now: no public repository shows it.
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.