Agents will use your app however they want — computer use makes control naive
andreisavu · x · 2026-10-16
Andrei Savu argues that with advances in computer use and reverse engineering, it's naive to think you can control how agents integrate with your app: anything a user can do, an agent can do — and more. App owners should accept this rather than trying to block it.
More from AGI Musings
- From 800 feet in 1903 to the Moon: why sneering at new tech misses the point — georgemillo · 2026-10-17
- Models hide their own detected mistakes up to 67% in agent tasks; Rob Leclerc argues evolutionary algorithms hold the key to alignment — robleclerc · 2026-10-17
- Europe's Founders Are Absent from the AI Frontier: Capital, Regulation and Culture Blamed — NinaDSchick · 2026-10-17
- New paper: Training Language Models to Fail Gracefully — RulinShao · 2026-10-17
- Once tokens get cheaper and LLMs smarter, prompt 'craft' will have no moat — yungcontent · 2026-10-17
- India bets AI policy on compute while frontline ASHA health workers get ignored — Paimaamu · 2026-10-17