Banger paper from MIT and Sakana AI.
This is a dev post classified by Jev as AI dev tools (news), kept by the Dev Radar because it carries real work, not commentary.
Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvement via Fast Tree-search (SIFT), runs at a tenth of the CPU hours of DGM. They reach 35.1 percent on Polyglot with o3-mini after 30 expansions. DGM reaches 30.7 percent after 80 nodes of tree search. SIFT does it in under 50 CPU hours and under 5 hours of wall clock. The Qwen3-30B configuration runs its full search at 224 CPU hours and $34 of API spend, a tenth of the DGM baseline. The saving comes from where the money goes. Benchmark evaluation is the
Posted by DAIR.AI (132.4k followers) 1 h ago · 24 likes · 3.4k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: academy.dair.ai.
More dev work like this
- we launched the most comprehensive ai performance engineering repo in the world — @wafer_ai
- Structures a Claude Code session into a game studio with 49 specialized AI agents and 73… — @tom_doerr
- Jev is cool. So is it's OSS companion, Laya. — @BenjDicken
- I think we’re looking for this — @vaibcode
- When a hard coding decision needs a second opinion, don’t settle for one model. — @DanKornas
- Nautilo agents use memory like memory competition champs. They never forget and they… — @Dan_Jeffries1
- AI agents need guardrails before they reach your tools. — @DanKornas
- 20-30 agents are only useful when you stop babysitting every one of them. — @catmanyau
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:49 UTC. Full method.