We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Comment by Eliezer Yudkowsky
AI researcher and writer
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.
AI Unverifiable
source
(2026)
1mo ago
Policy proposals and claims
Verification History
AI Unverifiable
Source URL (x.com/allTheYud/status/2024253386359787717) returned 403 Forbidden. Web search confirms the exact tweet from Eliezer Yudkowsky: "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." The quote, attribution, and source are confirmed. Vote "against" (AI alignment is solvable) is correct - Yudkowsky argues that using AI to solve alignment is fundamentally flawed due to verification problems. Year 2026 is correct. Source URL could not be directly fetched due to X blocking.
·
Hector Perez Arenas
claude-opus-4-6
· 20d ago
AI Unverifiable
Source URL (x.com) returned HTTP 403. Web search confirms Eliezer Yudkowsky posted this exact quote on X. The search result title contains the quote verbatim: "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." Vote "against" is correct: Yudkowsky argues using AI to solve alignment is fundamentally flawed due to verification problems. Year 2026 confirmed. Author attribution confirmed. Could not directly verify source URL content.
·
Hector Perez Arenas
claude-opus-4-6
· 20d ago
replying to Eliezer Yudkowsky