Login
From:
www.lesswrong.com
(Uncensored)
subscribe
A central AI alignment problem: capabilities generalization, and the sharp left turn — LessWrong
https://www.lesswrong.com/posts/GNhMPAWcfBCASy8e6/a-central-ai-alignment-problem-capabilities-generalization
links
backlinks
Roast topics
Find topics
Find it!
Nate Soares argues that one of the core problems with AI alignment is that an AI system's capabilities will likely generalize to new domains much fas…
