flâneur — a map of the web's best reading

How do we (more) safely defer to AIs? — LessWrong

lesswrong.com · 25,446 words · saved by 3 readers

As AI systems get more capable, it becomes increasingly uncompetitive and infeasible to avoid deferring to AIs on increasingly many decisions. Furthe…

x How do we (more) safely defer to AIs? — LessWrong AI-Assisted Alignment AI Frontpage 83 How do we (more) safely defer to AIs? by ryan_greenblatt , Julian Stastny 12th Feb 2026 AI Alignment Forum 87 min read 5 83 Ω 43 As AI systems get more capable, it becomes increasingly uncompetitive and infeasible to avoid deferring to AIs on increasingly many decisions. Further, once systems are sufficiently capable, control becomes infeasible . [1] Thus, one of the main strategies for handling AI risk is fully (or almost fully) deferring to AIs on managing these risks. Broadly speaking, when I say "defe

Explore this link on the map →

saved by

related reading