Dalmert

Karma: 63

OpenAI Superalignment: Weak-to-strong generalization

Dalmert14 Dec 2023 19:47 UTC

25 points

3 comments1 min readLW link

(openai.com)

Interview with Paul Christiano: How We Prevent the AI’s from Killing us

Dalmert27 Apr 2023 14:39 UTC

12 points

0 comments1 min readLW link

(www.youtube.com)

[Question] Personal predictions for decisions: seeking insights

Dalmert15 Feb 2023 6:45 UTC

4 points

4 comments5 min readLW link