Charbel-Raphaël

Karma: 2,162

Charbel-Raphael Segerie

https://crsegerie.github.io/

Living in Paris

Improvement on MIRI’s Corrigibility

WCargo and Charbel-Raphaël

Jun 9, 2023, 4:10 PM

54 points

8 comments13 min readLW link

Thriving in the Weird Times: Preparing for the 100X Economy

Lucie Philippon and Charbel-Raphaël

May 8, 2023, 1:44 PM

23 points

16 comments2 min readLW link

Davidad’s Bold Plan for Alignment: An In-Depth Explanation

Charbel-Raphaël and Gabin

Apr 19, 2023, 4:09 PM

168 points

40 comments21 min readLW link 2 reviews

New Hackathon: Robustness to distribution changes and ambiguity

Charbel-RaphaëlJan 31, 2023, 12:50 PM

12 points

3 comments1 min readLW link

Compendium of problems with RLHF

Charbel-RaphaëlJan 29, 2023, 11:40 AM

120 points

16 comments10 min readLW link

[Question] Don’t you think RLHF solves outer alignment?

Charbel-RaphaëlNov 4, 2022, 12:36 AM

9 points

23 comments1 min readLW link

Easy fixing Voting

Charbel-RaphaëlOct 2, 2022, 5:03 PM

12 points

2 comments1 min readLW link

Open application to become an AI safety project mentor

Charbel-RaphaëlSep 29, 2022, 11:27 AM

10 points

0 comments1 min readLW link

(docs.google.com)

[Question] Help me find a good Hackathon subject

Charbel-RaphaëlSep 4, 2022, 8:40 AM

6 points

18 comments1 min readLW link

[Question] How to impress students with recent advances in ML?

Charbel-RaphaëlJul 14, 2022, 12:03 AM

12 points

2 comments1 min readLW link

[Question] Is it desirable for the first AGI to be conscious?

Charbel-RaphaëlMay 1, 2022, 9:29 PM

5 points

12 comments1 min readLW link