NVIDIA and MIT researchers pointed Karpathy's loop at the agent harness itself and cut…
This is a vibe coding post classified by AGK Intelligence as Agent infra & costs (a workflow), kept by the Vibe Coding Radar because it carries real work, not commentary.
NVIDIA and MIT researchers pointed Karpathy's loop at the agent harness itself and cut the API bill by 50-54% same models, same benchmark. only the harness around Claude Code and Codex changed the loop they ran on it: propose -> implement -> review -> test -> keep or discard the 4 changes that survived: 1. edit a file and run its test in one tool call 2. compact context only after a finished step, and only when it saves more than it costs 3. archive huge outputs and pass on a short excerpt plus a handle 4. hand log reading to a cheaper model, then check its evidence against the original th
Posted by Mr. Buzzoni (28.4k followers) 4 days ago · 239 likes · 14.5k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs.
More vibe coding work like this
- Build an agent on @onkeiki to answer your customers while you sleep. — @orchid_hq
- how do you stop 20+ agents from colliding on the same client work? — @webjuice_ie
- Brilliant paper on optimizing agent environments. — @dair_ai
- Docker is one box. The coding agent can run in others, and switching is one line 🧰 — @marcelotryle
- Holy f*cking sh*t... everyone upgrades Claude and nobody builds the harness — @gippp69
- 1/9 — @TollyLabs
- As AI coding agents get more capable, knowing what they're doing becomes just as… — @EntelligenceAI
- btw in Portals you can now manage your agent CLI versions, update them, and view their… — @imnotchalk
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. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:18 UTC. Full method.