1.7B model shown driving browser and writing HTML autonomously, claimed to hit 4o-level benchmarks
JosephJacks_ · x · 2026-11-12
User @0xSero shows a tiny 1.7B-parameter model operating a browser, generating HTML files, and managing itself inside Pi — a full agent-style workflow.
The poster claims it hits GPT-4o levels on most benchmarks and calls it great for workflow automations. Unverified personal demo, but if accurate it suggests very small models can already handle basic agentic tasks.
More from coding & agent
- AI-Generated PRs Are Drowning Open Source: Merging Now Requires Knowing a Maintainer — dbreunig · 2026-11-12
- 133 GPT-6 agents spend 6 days tuning Stockfish NNUE weights, gaining +17.66 Elo in 256-game match — imjustnewatai · 2026-11-12
- sokrypton: AI models are still terrible at coding — terminals made them usable, wet labs could do the same for biology — yuvalpi · 2026-11-12
- sokrypton: AI got usable at coding via terminal iteration — wet labs could do the same for biology — sokrypton · 2026-11-12
- Building a mangrove forest simulator with a swarm of Carbon agents citing 45 papers — AI_Andrew · 2026-11-12
- Fumadocs 16.19 adds runtime variables and branching without leaking hidden branches — bclavie · 2026-11-12