RSS

Marie_DB

Karma: 153

An al­ign­ment safety case sketch based on debate

8 May 2025 15:02 UTC
57 points
19 comments25 min readLW link
(arxiv.org)

UK AISI’s Align­ment Team: Re­search Agenda

7 May 2025 16:33 UTC
110 points
2 comments11 min readLW link