Anton Zheltoukhov

• Anton Zheltoukhov 24 Jul 2025 8:54 UTC

  0 points

  3 ∶ 3

  on: How did the AI Safety tal­ent pipeline come to work so well?

  that’s just false. alignment community even to this day is significantly less then 1000 people worldwide. i would not call that a success. i’m not blaming the people involved. they’ve done what they could. lets just not deceive ourselves here

• Anton Zheltoukhov 17 Apr 2025 16:54 UTC

  0 points

  2 ∶ 1

  on: Align­ment is not *that* hard

  current safety techniques offer almost no value for the real alignment problems that we are starting to face
  
  https://​​www.lesswrong.com/​​posts/​​HmQGHGCnvmpCNDBjc/​​current-ais-provide-nearly-no-data-relevant-to-agi-alignment#ponxMRXsnDJNyY4YX