Irving: pauses and reversals would push AI developers toward higher alignment confidence
geoffreyirving · x · 2026-09-10
Wrapping up his thread, Geoffrey Irving reiterates: "If we get more time, we can spend it." Time would go toward Paul's day-job alignment work and orgs like Resolution for more rigorous alignment attempts, while pauses and reversals would better incentivize AI developers to aim for higher confidence.
More from AGI Musings
- AI safety discourse is replaying 2020's pandemic expert free-for-all — SanhEstPasMoi · 2026-09-10
- Train on Frontier Papers or Build RL Envs? An Insider Debate on Math Model Training — ctjlewis · 2026-09-10
- AI extinction drama: researchers believe in the risk yet keep racing, says viral thread — AIandDesign · 2026-09-10
- François Fleuret asks: what intellectual endeavor can humanity still claim from AI in two years? — francoisfleuret · 2026-09-10
- That Proof Was Downstream of Mathematicians' Chats — but Is 'Direct Training' Even Real? — shaurizard · 2026-09-10
- Debate sparks: Banks' Culture series already wrote the definitive AGI utopia — Promptmethus · 2026-09-10