Eliezer Yudkowsky

Make immediate multinational agreements to prevent the prohibited activities from moving elsewhere. [...] preventing AI extinction scenarios is considered a priority above preventing a [...] nuclear exchange Unverified source (2023)

From our perspective, an AI will either be so slow as to be bottlenecked, or so fast as to be FOOM. [...] 'AI go FOOM'. AI Unverifiable source (2008)

The moratorium on new large training runs needs to be indefinite and worldwide. There can be no exceptions, including for governments or militaries. If the policy starts with the U.S., then China needs to see that the U.S. is not seeking an advantage... more Verified source (2023)

I have heard zero people advocating "make AI do our ASI alignment homework" show they understand the elementary computer science of why that's hard: you can't verify inside a loss function whether a proposed ASI alignment scheme is any good. Unverified source (2026)

Many researchers steeped in these issues, including myself, expect that the most likely result of building a superhumanly smart AI, under anything remotely like the current circumstances, is that literally everyone on Earth will die. Not as in “maybe... more AI Unverifiable source (2023)