Свежие переводы
Свежие посты с LessWrong.com
- Dialogue with Gabriel Alfour on Emergent Wisdom, Coordination, Growing Up, and Democratic Republicanism
- OpenAI: Astra covertly underperforms on safety research
- Against Moloch #50
- Fun toy result: a subliminal-learning effect via on-policy distillation
- Model's "emotions" noticeably change when they take risky actions


