Свежие переводы
Свежие посты с LessWrong.com
- Even if others are less responsible you can still make things worse
- Fixed-weight models are adversarially vulnerable: hence misaligned
- The Alignment Community Is Unintentionally Building a Censor's Toolkit
- My Second End of the World
- The likely outcome of an AI pause is that we unpause too early and everyone dies


