Super interesting work from Zoom and colleagues.
This is a vibe coding post classified by Jev as Coding agents (a free resource), kept by the Vibe Coding 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) 18 h ago · 20 likes · 2.7k views · view the original post on X. Kept by the Vibe Coding Radar as Coding agents.
More vibe coding work like this
- New plugin alert: Make your sidebar behave like Cursor's — @get_bb_app
- We built a plugin that gives Jev a browser in Cline, and have been blown away by the… — @cline
- i gave claude the link to the tweet and it shipped — @peer_rich
- Thanks a lot, @tobi — @iam_zachi
- I literally complained today lol — @Rasmic
- I found a most interesting Android agent project built by Google — @hasantoxr
- You can literally hand claude code a competitor's linkedin post and it: — @itsalexvacca
- Codex’s mobile remote mode is seriously underrated. — @godofprompt
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. 1.8k posts from 1.8k X accounts over the last 14 days, 141 tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 01:18 UTC. Full method.