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.

Original post →

More from AGI Musings

AGI Musings channel →