Jared Palmer runs overnight autoresearch with Devin on Modal to improve a 0.6B model
AAAzzam · x · 2026-09-19
Jared Palmer demonstrates an autoresearch workflow: he set up Devin to run training experiments overnight on Modal to produce an improved Qwen3-0.6B checkpoint. He previously open-sourced Kev-0.5B, a tiny decision model based on Qwen2.5-0.5B with a TypeSafe-compatible API that can be trained and run on a MacBook Pro, with weights and model card on GitHub.
More from coding & agent
- DeepTeam: Open-source framework for red teaming LLMs locally — tom_doerr · 2026-09-19
- LangGraph Team on 3 Years of 'Graph Engineering': jev Fits Graph Classification Steps — hwchase17 · 2026-09-19
- Craft Agent Scans Its Own Codebase and Produces a Promo Video Unprompted — op7418 · 2026-09-19
- Open-Source Skill Turns Your Codebase into a Polished Product Promo Video via Claude Code — op7418 · 2026-09-19
- Gemini CLI PR adds 'gemini models list' with pure JSON output for tool integrations — Kaushik2210 · 2026-09-19
- Claude Code 2.1.278 moves Auto mode classifier server-side, ending classifier overhead charges — ClaudeCodeLog · 2026-09-19