ThePrimeagen's Desktop QA Agent: Cut QEMU Runs From 15 Minutes to 2, Still Too Slow
cyrus_zei · x · 2026-10-06
ThePrimeagen shares progress on his Omarchy QA agent, flagging the two hard problems: making agents fast in an era of very slow agents, and defining what "correct" even means to test. His agent crawling the desktop in QEMU initially took 15 minutes just to unlock and verify the desktop; optimizations brought the median to 5, then a custom harness to 2 minutes—which he still considers too slow as he keeps experimenting. A commenter suggests looking into AT-SPl2 for element-level control of Arch.
More from coding & agent
- Dev builds native Mac app to message multiple AI agents simultaneously — msg · 2026-10-06
- Dev uses GitHub Copilot app to generate a rebuildable 60s hype video via PR — DanWahlin · 2026-10-06
- Oxylabs raises $130M at $3.6B valuation, first outside capital, betting on AI agents — Ronangmi · 2026-10-06
- PM open-sources GitDocket: manage AI coding epics, tasks and wikis in Git — bjorgen · 2026-10-06
- Amelia Wattenberger: AI is still in its terminal era, and GUI history holds lessons — Wattenberger · 2026-10-06
- Ex-Shopify principal designer Eric Hu joins Cognition as principal designer — Kyrannio · 2026-10-06