Свежие переводы
Свежие посты с LessWrong.com
- Robust Finite Policies are Nontrivially Structured
- In (highly contingent!) defense of interpretability-in-the-loop ML training
- Spectral Signatures of Gradual Disempowerment
- Demands Are All You Need: Prompt Imperativeness Drastically Reduces Hedging In LLMs (n=900, Cohen's d = 2.67)
- If all humans were turned into high-fidelity mind uploads tomorrow, would we be self-sustaining?
