Great new paper on recursive self-improvement.
This is a dev post classified by AGK Intelligence as AI dev tools (a free resource), kept by the Dev Radar because it carries real work, not commentary.
Great new paper on recursive self-improvement. Self-improving AI is one of the most discussed ideas right now. This paper explores training a model to run LLM post-training itself. (bookmark it) The team built RSI-Craft, a pipeline that turns research papers into executable training environments, including datasets, metrics, and evaluation code. After filtering for reliability and difficulty, 281 post-training tasks remain. Frontier models solved them under an improved harness, and the filtered trajectories were used to fine-tune Qwen models. The 9B version gains 8.74 points. RSI-Dojo-35B-
Posted by DAIR.AI (136.7k followers) 3 h ago · 39 likes · 3.2k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- “AI is now improving the systems that run AI.” Thanks to @Forbes for covering Together… — @togethercompute
- Hy4 beat DeepSeek at remaking the GTA VI trailer 🎬 — @aimlapi
- Stop rebuilding your LinkedIn writing prompts from scratch. — @DanKornas
- Google Research 开源了 Harness²，让 Agent 自己去改外面那层配置，跑一轮下来在 WorkBuddy-Bench 上最多涨了 11.5 分。 — @bkdgiffug
- The real test of AI coding is what happens when the next agent builds on it. — @wallstengine
- We got Unsloth quants for Qwen3.8-Flash-Next, again. — @ItsmeAjayKV
- INSANE. Axiom just announced the formalization of the ENTIRE 7,500-page Stacks Project,… — @choblin29
- Tencent Hy4 from @TencentHunyuan is now supported in OpenClaw. — @openclaw
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 18:20 UTC. Full method.