Book Review: How Minds Change

bc4026bd4aaa5b7fe25 May 2023 17:55 UTC

221 points

29 comments15 min readLW link

Focus on the places where you feel shocked everyone’s dropping the ball

So8res2 Feb 2023 0:27 UTC

380 points

58 comments4 min readLW link

Steering GPT-2-XL by adding an activation vector

TurnTrout, Monte M, David Udell, lisathiergart and Ulisse Mini

13 May 2023 18:42 UTC

378 points

73 comments50 min readLW link

How to have Polygenically Screened Children

GeneSmith7 May 2023 16:01 UTC

280 points

67 comments29 min readLW link

Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment

elspood21 Jun 2022 23:55 UTC

341 points

41 comments7 min readLW link

Study Guide

johnswentworth6 Nov 2021 1:23 UTC

257 points

44 comments16 min readLW link

Why I think strong general AI is coming soon

porby28 Sep 2022 5:40 UTC

312 points

138 comments34 min readLW link

Can we efficiently distinguish different mechanisms?

paulfchristiano27 Dec 2022 0:20 UTC

86 points

30 comments16 min readLW link

(ai-alignment.com)

(My understanding of) What Everyone in Technical Alignment is Doing and Why

Thomas Larsen and elifland

29 Aug 2022 1:23 UTC

388 points

87 comments38 min readLW link

AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC

839 points

670 comments30 min readLW link

Lies Told To Children

Eliezer Yudkowsky14 Apr 2022 11:25 UTC

348 points

89 comments7 min readLW link

More information about the dangerous capability evaluations we did with GPT-4 and Claude.

Beth Barnes19 Mar 2023 0:25 UTC

233 points

52 comments8 min readLW link

(evals.alignment.org)

Science in a High-Dimensional World

johnswentworth8 Jan 2021 17:52 UTC

269 points

53 comments7 min readLW link 1 review

When is Goodhart catastrophic?

Drake Thomas and Thomas Kwa

9 May 2023 3:59 UTC

145 points

18 comments8 min readLW link

“Other people are wrong” vs “I am right”

Buck22 Feb 2019 20:01 UTC

241 points

20 comments9 min readLW link 2 reviews

Rereading Atlas Shrugged

Vaniver28 Jul 2020 18:54 UTC

153 points

28 comments13 min readLW link 1 review

Predictable updating about AI risk

Joe Carlsmith8 May 2023 21:53 UTC

272 points

20 comments36 min readLW link

Real-Life Examples of Prediction Systems Interfering with the Real World (Predict-O-Matic Problems)

NunoSempere3 Dec 2020 22:00 UTC

122 points

28 comments9 min readLW link

What 2026 looks like

Daniel Kokotajlo6 Aug 2021 16:14 UTC

414 points

146 comments16 min readLW link 1 review

The shard theory of human values

Quintin Pope and TurnTrout

4 Sep 2022 4:28 UTC

232 points

61 comments24 min readLW link