flâneur — a map of the web's best reading

The case for ensuring that powerful AIs are controlled — LessWrong

lesswrong.com · 28,274 words · saved by 9 readers

In this post, we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they appl…

x The case for ensuring that powerful AIs are controlled — LessWrong Best of LessWrong 2024 AI Control Redwood Research Deceptive Alignment AI Curated 290 The case for ensuring that powerful AIs are controlled by ryan_greenblatt , Buck 24th Jan 2024 AI Alignment Forum 34 min read 74 290 Ω 114 In this post, we argue that AI labs should ensure that powerful AIs are controlled . That is, labs should make sure that the safety measures they apply to their powerful models prevent unacceptably bad outcomes, even if the AIs are misaligned and intentionally try to subvert those safety measures. We thin

Explore this link on the map →

saved by

related reading