Proposed safety measures such as unhackable reward structures and monitoring an AI system's chain of thought reasoning remain unproven partial fixes, according to Paul Christiano
Agree
Disagree
Overview
Debates
Related claims
Topics
Sources
From the article
OpenAI board member worries an AI "takeover" of society could be months away
4
41e85161
Article
OpenAI board member worries an AI "takeover" of society could be months away
0
Opening sign-in…