No proof of safety for superintelligence is possible, argue X safety debaters
orthonormalist · x · 2026-09-21
A debate on superintelligence alignment: ctjlewis argues there can be no 'proof of safety' for SI in the way critics imagine—a superintelligent being offers no guarantees, and everything else is theater. orthonormalist replies that he agrees with many doomer facts but not the appropriate response to them. A representative clash over whether verifiable alignment is even possible.
More from AGI Musings
- Researcher willing to bet $100K the intelligence explosion won't happen next year — NathanpmYoung · 2026-11-12
- ICLR reviewer: the worst parts of my job are reading and answering AI slop — chhaviyadav_ · 2026-11-12
- Fermi paradox twist: advanced civilizations may go digital after developing AI — VraserX · 2026-11-12
- Mark Cuban: AI could make healthcare costs 'drop like a rock' — alvelda · 2026-11-12
- Researcher's paradox: if AI makes everyone unemployed, who pays for tokens? — prajdabre · 2026-11-12
- Dear ImGui Creator ocornut: AI Empowers Mediocre Makers to Produce More Mediocrity, Faster — rms80 · 2026-11-12