RSS

Judd Rosenblatt

Karma: 1,433

CEO at AE Studio

Mis­tral Large 2 (123B) seems to ex­hibit al­ign­ment faking

27 Mar 2025 15:39 UTC
81 points
4 comments13 min readLW link

Re­duc­ing LLM de­cep­tion at scale with self-other over­lap fine-tuning

13 Mar 2025 19:09 UTC
162 points
46 comments6 min readLW link

Align­ment can be the ‘clean en­ergy’ of AI

22 Feb 2025 0:08 UTC
68 points
8 comments8 min readLW link

Mak­ing a con­ser­va­tive case for alignment

15 Nov 2024 18:55 UTC
208 points
67 comments7 min readLW link

Science ad­vances one funeral at a time

1 Nov 2024 23:06 UTC
100 points
9 comments2 min readLW link

Self-pre­dic­tion acts as an emer­gent regularizer

23 Oct 2024 22:27 UTC
92 points
9 comments4 min readLW link

The case for a nega­tive al­ign­ment tax

18 Sep 2024 18:33 UTC
79 points
20 comments7 min readLW link

The EA case for Trump

Judd Rosenblatt3 Aug 2024 1:00 UTC
14 points
1 comment1 min readLW link
(www.secondbest.ca)

Self-Other Over­lap: A Ne­glected Ap­proach to AI Alignment

30 Jul 2024 16:22 UTC
238 points
53 comments12 min readLW link2 reviews

Yoshua Ben­gio: Rea­son­ing through ar­gu­ments against tak­ing AI safety seriously

Judd Rosenblatt11 Jul 2024 23:53 UTC
72 points
3 comments1 min readLW link
(yoshuabengio.org)

There Should Be More Align­ment-Driven Startups

31 May 2024 2:05 UTC
62 points
14 comments11 min readLW link

Key take­aways from our EA and al­ign­ment re­search sur­veys

3 May 2024 18:10 UTC
113 points
10 comments21 min readLW link

AE Stu­dio @ SXSW: We need more AI con­scious­ness re­search (and fur­ther re­sources)

26 Mar 2024 20:59 UTC
67 points
8 comments3 min readLW link

Sur­vey for al­ign­ment re­searchers!

2 Feb 2024 20:41 UTC
71 points
11 comments1 min readLW link

The ‘Ne­glected Ap­proaches’ Ap­proach: AE Stu­dio’s Align­ment Agenda

18 Dec 2023 20:35 UTC
190 points
23 comments12 min readLW link1 review