Asking (Some Of) The Right Questions
"对齐问题" 相关文章
Space colonization and scientific discovery could be mandatory for successful defensive AI
Until the stars burn out? Assessing the stakes of AGI lock-in
We won’t get docile, brilliant AIs before we solve alignment
THE WISE, THE GOOD, THE POWERFUL
Generalization and the Multiple Stage Fallacy?
Generalization and the Multiple Stage Fallacy?
Generalization and the Multiple Stage Fallacy?
Nice-ish, smooth takeoff (with imperfect safeguards) probably kills most "classic humans" in a few decades.
AI Risk: Can We Thread the Needle? [Recorded Talk from EA Summit Vancouver '25]
AI Risk: Can We Thread the Needle? [Recorded Talk from EA Summit Vancouver '25]
Why Corrigibility is Hard, and Important [IABED Resources]
Superintelligence could wipe us out if we rush into it — but humanity can still pull back, a top AI safety expert says
More Reactions to If Anyone Builds It, Everyone Dies
Red-Thing-Ism
Emergent Misalignment on a Budget
Maximal Curiousity is Not Useful
Training-time schemers vs behavioral schemers
Why do misalignment risks increase as AIs get more capable?
A response to OpenAI’s “How we think about safety and alignment”
