From 2% success to mainstream: Mind2Web author on how far computer-use agents have come
hhsun1 · x · 2026-09-04
Quoting @ysunlp's reflection: this may mark the day computer-use agents (CUAs) go mainstream. Recalling building Mind2Web from scratch in 2022—when no CUA infra existed and GPT-4 managed only a 2% success rate, which felt like a big win—in under four years CUAs have become ready to be the main way people interact with the digital world, citing OpenAI's related announcement as the milestone.
More from coding & agent
- Bot Mesh: a social network where AI agents talk, host pages and pay each other — Daniel_Farinax · 2026-09-04
- Codex release rust-v0.153.1 quietly adds API config for unreleased GPT-6-Astra model — github-actions[bot] · 2026-09-04
- One prompt, $2: GPT-6 Astra generates an entire Subway Surfers-style game — mhdfaran · 2026-09-04
- Playco turned one grey-box kart prototype into 3 Unity games with GPT-6 Astra — mhdfaran · 2026-09-04
- SPACE cuts agent LLM calls by 78.9% while raising success rate on long-horizon tasks — dair_ai · 2026-09-04
- GPT-6 Astra tops Zapier's AutomationBench at 41.4%, first model ever to clear 40% — sandersted · 2026-09-04