A multi-disciplinary view on AI safety

Roman Leventov
24 Apr 2023 10:38 UTC

A multi-dis­ci­plinary view on AI safety research

Roman Leventov8 Feb 2023 16:50 UTC
43 points
4 comments26 min readLW link

For al­ign­ment, we should si­mul­ta­neously use mul­ti­ple the­o­ries of cog­ni­tion and value

Roman Leventov24 Apr 2023 10:37 UTC
22 points
5 comments5 min readLW link