RSS

research_prime_space

Karma: 52

LLMs are likely not conscious

research_prime_space29 Sep 2024 20:57 UTC
6 points
9 comments1 min readLW link

Ex­cit­ing New In­ter­pretabil­ity Paper!

research_prime_space9 May 2023 16:39 UTC
12 points
1 comment1 min readLW link

Pe­nal­ize Model Com­plex­ity Via Self-Distillation

research_prime_space4 Apr 2023 18:52 UTC
15 points
7 comments1 min readLW link

Cap Model Size for AI Safety

research_prime_space6 Mar 2023 1:11 UTC
0 points
4 comments1 min readLW link

Sim­ple Way to Prevent Power-Seek­ing AI

research_prime_space7 Dec 2022 0:26 UTC
12 points
1 comment1 min readLW link