RSS

tchauvin

Karma: 102

AI safety and cybersecurity

https://​​tchauvin.com

End-to-end hack­ing with lan­guage models

tchauvinApr 5, 2024, 3:06 PM
29 points
0 comments8 min readLW link

An Overview of AI risks—the Flyer

Jul 17, 2023, 12:03 PM
20 points
0 comments1 min readLW link
(docs.google.com)

[Question] Is there an anal­y­sis of the com­mon con­sid­er­a­tion that split­ting an AI lab into two (e.g. the found­ing of An­thropic) speeds up the de­vel­op­ment of TAI and there­fore in­creases AI x-risk?

tchauvinMar 16, 2023, 2:16 PM
4 points
0 comments1 min readLW link

Us­ing spaced rep­e­ti­tion to make the most out of blog posts and books

tchauvinDec 21, 2020, 2:47 AM
10 points
1 comment3 min readLW link