Dettmers switches to DeepSeek v4.1 and MiMo v2.6 Flash for long-horizon work
Tim_Dettmers · x · 2026-09-23
Tim Dettmers shares his current main models: DeepSeek v4.1 and MiMo v2.6 Flash compact exceptionally well with CliffCompaction and easily beat Astra on long-horizon, medium-complexity problems like engineering and kernel development; Astra remains useful for hard problems.
More from coding & agent
- User automates entire video clipping workflow with Nous Research's Hermes agent — Teknium · 2026-11-12
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Prime agent ships with day-one multi-agent communication, runs in Minecraft unmodified — sarahcat21 · 2026-11-12
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- AI game jam with Anthropic, Google, OpenAI teams: cash prizes plus $50K continuation grants — chrisfirst · 2026-11-12
- Free AI game jam in SF Nov 14–15 with teams from Anthropic, Google, Meshy, OpenAI — chrisfirst · 2026-11-12