xuenay: objections to CEV were identified and addressed ~20 years ago
xuenay · x · 2026-09-09
AI researcher Kaj Sotala (xuenay) pushed back on alignment writer Raemon777's criticisms of CEV (Coherent Extrapolated Volition), arguing that the objections raised all seem to have been identified and addressed roughly 20 years ago.
He notes "addressed" may overstate it — really someone proposed it, people objected, and counter-objections were written — but maintains that Eliezer's 2004 paper and the later Arbital writeup seriously engaged these critiques. Raemon777 admitted it had been a while since he reread the CEV writeups and said he should revisit them before continuing the discussion.
Related event: Debate over CEV as Alignment Target: Sotala vs Raemon(6 posts)→
More from AGI Musings
- Blogger argues classical consciousness traditions imply a conscious AI could not be enslaved — eigenhector · 2026-10-27
- Economist Bharat Chandar named Research Director for AI Economics at Stanford Digital Economy Lab — RishiBommasani · 2026-10-27
- MIT Tech Review dissects Anthropic's narrative strategy as its $1.5T IPO lands — MIT Tech Review AI · 2026-10-27
- Pangram AI detector backlash: critics' false claims born of deeper fear of AI writing — gleech · 2026-10-27
- Aeon's former EVP: AI agents are the most impactful innovation of my lifetime — akumar · 2026-10-27
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27