Super interesting work from Zoom and colleagues.
This is a dev post classified by Jev as AI dev tools (a free resource), kept by the Dev Radar because it carries real work, not commentary.
Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed and varied planning, the action space, and context management one at a time. They did across 176 matched settings, four models, SWE-Bench Verified and Terminal-Bench 2.1. Context management pays off more as the context window tightens. Most of its benefit comes from preventing overflow failures rather than from better reasoning. Staging rule-based elision before LLM summarization gave the be
Posted by DAIR.AI (132.4k followers) 20 h ago · 124 likes · 9.3k 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
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
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. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.