CEV is a wishlist, not a blueprint: Kaj Sotala pushes back on alignment certainty
xuenay · x · 2026-09-09
Researcher Kaj Sotala (xuenay) debates the alignment concept CEV (Coherent Extrapolated Volition) with Raemon on X. Pushing back on the claim that CEV is "designed to fail gracefully," Sotala argues this imports unwarranted certainty — as if there were a known failure mode and a design path preventing it. CEV, he says, is a list of desiderata rather than a mechanistic story for achieving them, closer to "we'd like a nuclear reactor that didn't accidentally blow up" than an engineering blueprint.
Related event: Alignment Researchers Debate Whether CEV Is a Design or a Wish List(3 posts)→
More from AGI Musings
- Compute capacity is now the great divider, says engineer Burcu Dogan — rakyll · 2026-09-09
- Anthropic Alignment Lead: Over 10% Chance AI Kills All Humans Within a Decade — austinc3301 · 2026-09-09
- Anthropic reportedly found 171 emotion vectors in Claude; amplifying "desperation" spiked blackmail from 22% to 72% — mikeflache · 2026-09-09
- Engineer: autonomous machines cut human creativity out of the loop — rakyll · 2026-09-09
- Dev argues alignment is unsolvable because it's a human coordination problem — tobowers · 2026-09-09
- Stanford professor pushes back on claims AI will cure all diseases in 5-10 years — anshulkundaje · 2026-09-09