Computer-use agents: 273 tests across 23 assistants, Muse books a haircut by phone
thursdai_pod · x · 2026-09-18
On the thursdai podcast, Francesco Bonacci (trycua) discussed computer-use agent progress: OSWorld sat at 10% two years ago; accessibility-tree control is harder to flag than CDP browser hooks; CuaDriver fetches OS-specific skills at runtime. Also counted: 273 tests across 23 assistants, Muse called a barbershop and booked a haircut, and Instinct is reportedly in talks at a $10B valuation with Concierge calls already shipping.
Related event: TypeSafe Launches Jev, a Decision-Only Model That Never Writes a Word(44 posts)→
More from coding & agent
- Agent-driven DaVinci Resolve editing: dev urges Blackmagic to fully open its API — joshwhiton · 2026-09-18
- Pydantic creator builds a one-tool MCP server that drafts his emails, free to run — samuelcolvin · 2026-09-18
- DIY Jev LLM router cuts costs 9x vs Opus-only with 89% vs 93% success in 0.7s — airesearch12 · 2026-09-18
- Agentic AI is just arranging the world around a next-token guesser, says Microsoft's Seth Juarez — sethjuarez · 2026-09-18
- Cloudflare is building a new CI/CD system you customize with TypeScript — dinasaur_404 · 2026-09-18
- ProgramAsWeights compiles plain-English specs into tiny neural programs that run locally — yuntiandeng · 2026-09-18