AI alignment researchers don’t (seem to) stack

So8res21 Feb 2023 0:48 UTC

194 points

40 comments3 min readLW link

What links here?

The Learning-Theoretic Agenda: Status 2023 by Vanessa Kosoy (19 Apr 2023 5:21 UTC; 144 points)
AI Safety − 7 months of discussion in 17 minutes by Zoe Williams (EA Forum; 15 Mar 2023 23:41 UTC; 90 points)
How I learned to stop worrying and love skill trees by junk heap homotopy (23 May 2023 4:08 UTC; 83 points)
AI #2 by Zvi (2 Mar 2023 14:50 UTC; 66 points)
Try to solve the hard parts of the alignment problem by Mikhail Samin (18 Mar 2023 14:55 UTC; 54 points)
PonPonPon's comment on A rough and incomplete review of some of John Wentworth’s research by So8res (28 Mar 2023 22:31 UTC; 43 points)
United We Align: Harnessing Collective Human Intelligence for AI Alignment Progress by Shoshannah Tekofsky (20 Apr 2023 23:19 UTC; 41 points)
EA & LW Forum Weekly Summary (20th − 26th Feb 2023) by Zoe Williams (EA Forum; 27 Feb 2023 3:46 UTC; 29 points)
An open letter to SERI MATS program organisers by Roman Leventov (20 Apr 2023 16:34 UTC; 26 points)
AI Safety − 7 months of discussion in 17 minutes by Zoe Williams (15 Mar 2023 23:41 UTC; 25 points)
How I learned to stop worrying and love skill trees by Clark Urzo (EA Forum; 23 May 2023 8:03 UTC; 22 points)
Part 3: A Proposed Approach for AI Safety Movement Building: Projects, Professions, Skills, and Ideas for the Future [long post][bounty for feedback] by PeterSlattery (EA Forum; 22 Mar 2023 0:54 UTC; 22 points)
Why is LW not about winning? by azergante (13 Jul 2025 22:36 UTC; 21 points)
trevor's comment on The Kids are Not Okay by Zvi (8 Mar 2023 18:24 UTC; 20 points)
A Proposed Approach for AI Safety Movement Building: Projects, Professions, Skills, and Ideas for the Future [long post][bounty for feedback] by peterslattery (22 Mar 2023 1:11 UTC; 14 points)
Try to solve the hard parts of the alignment problem by MikhailSamin (EA Forum; 11 Jul 2023 17:02 UTC; 8 points)
Should you increase AI alignment funding, or increase AI regulation? by Knight Lee (26 Nov 2024 9:17 UTC; 7 points)
trevor's comment on On “Geeks, MOPs, and Sociopaths” by alkjash (20 Jan 2024 0:47 UTC; 7 points)
Contrapositive Natural Abstraction—Project Intro by Elliot Callender (24 Jun 2024 18:37 UTC; 4 points)
EA & LW Forum Weekly Summary (20th − 26th Feb 2023) by Zoe Williams (27 Feb 2023 3:46 UTC; 4 points)
Nicholas Kross's comment on Why Not Just… Build Weak AI Tools For AI Alignment Research? by johnswentworth (5 Mar 2023 17:05 UTC; 3 points)
Adam Zerner's comment on adamzerner’s Shortform by Adam Zerner (3 Mar 2023 6:24 UTC; 2 points)
The humanity’s biggest mistake by RomanS (10 Mar 2023 16:30 UTC; 0 points)

Crossposted to EA Forum (47 points, 3 comments)