Your Small AI Model Can Now Drive A Computer
Podcast: AI Breakdown ยท Varun Sirohi
Opublikowano: 2026-10-31
๐๐๐จ๐ฎ๐ญ ๐๐๐,๐๐๐ ๐จ๐ ๐ญ๐จ๐ค๐๐ง๐ฌ ๐ ๐จ๐ญ ๐ง๐จ๐ฐ๐ก๐๐ซ๐.๐๐๐จ๐ฎ๐ญ๐๐,๐๐๐ ๐ ๐จ๐ญ ๐ข๐ญ ๐ฐ๐จ๐ซ๐ค๐ข๐ง๐ ๐ข๐ง ๐ญ๐ฐ๐จ ๐ฐ๐๐๐ค๐ฌ. ๐ณ A developer set out to port the TypeScript compiler to Rust with AI. The same job, a twentieth of the spend, and the cheaper attempt is the one that worked. The README adds a line that should make any owner sit up. He has never read a line of this code. This week on ๐๐ก๐ ๐๐ ๐๐ซ๐๐๐ค๐๐จ๐ฐ๐ง: ๐๐ ๐๐ฌ ๐๐จ๐ฏ๐ข๐ง๐ ๐ญ๐จ ๐๐จ๐ฎ๐ซ ๐๐๐ฌ๐ค Nobody outside the project has confirmed how much human steering stood between the failure and the result, which is the honest footnote on every spectacular agent story. Inside the episode: ๐ด A small model scoring 72.4% on the offline OSWorld computer use benchmark, up from 15.7% for its predecessor, with the larger model still ahead at 83.9% ๐ด Input priced at 10 cents per million tokens against $1 for the previous version, a tenth of the cost ๐ด 39.2% on a command line benchmark...