RSS

Daniel Herrmann

Karma: 114

Still no Lie De­tec­tor for LLMs

Daniel Herrmann and ben_levinstein
18 Jul 2023 19:56 UTC
47 points
2 comments21 min readLW link

Bridg­ing Ex­pected Utility Max­i­miza­tion and Optimization

Daniel Herrmann5 Aug 2022 8:18 UTC
25 points
5 comments14 min readLW link

For­mal Philos­o­phy and Align­ment Pos­si­ble Projects

Daniel Herrmann30 Jun 2022 10:42 UTC
34 points
5 comments8 min readLW link

Choos­ing to Choose?

Daniel Herrmann10 Jul 2018 20:15 UTC
10 points
7 comments5 min readLW link