David Manheim: AI Loss-of-Control Risk Is About Oversight Limits, Not Instruction Following
davidmanheim · x · 2026-09-15
AI safety researcher David Manheim clarifies what loss-of-control risk actually means: not poor instruction following, but the lack of ability to perform reasonable oversight and the fundamental limits of specifying behavior for systems that are faster, smarter, or more narrowly capable than humans. He argues these problems are already visible today.
More from AGI Musings
- Debate Rekindled: Do Half of AI Researchers Really See 10% Extinction Risk? — NathanpmYoung · 2026-09-15
- "Twitter doesn't offer this filter": transformer-gatekeeping take stirs debate — generativist · 2026-09-15
- Can't sketch a transformer? Then stop weighing in on AI, researcher says — generativist · 2026-09-15
- Thom Wolf clashes with researcher over whether AI labs are only profit-driven — mervenoyann · 2026-09-15
- Researcher joins Stanford DigEconLab to simulate the economy with AI agents — soumitrashukla9 · 2026-09-15
- Dario Amodei's 'We Must Pace the Frontier' essay sparks wave of AI slowdown debate — The Verge AI · 2026-09-15