A Bear Case: My Predictions Regarding AI Progress

Thane Ruthenis5 Mar 2025 16:41 UTC

339 points

148 comments9 min readLW link

On the Rationality of Deterring ASI

Dan H5 Mar 2025 16:11 UTC

143 points

30 comments4 min readLW link

(nationalsecurity.ai)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley and Owain_Evans

25 Feb 2025 17:39 UTC

322 points

89 comments4 min readLW link

Judgements: Merging Prediction & Evidence

abramdemski23 Feb 2025 19:35 UTC

103 points

5 comments6 min readLW link

Eliezer’s Lost Alignment Articles / The Arbital Sequence

Ruby and RobertM

20 Feb 2025 0:48 UTC

207 points

9 comments5 min readLW link

How to Make Superbabies

GeneSmith and kman

19 Feb 2025 20:39 UTC

556 points

324 comments31 min readLW link

Levels of Friction

Zvi10 Feb 2025 13:10 UTC

138 points

6 comments12 min readLW link

(thezvi.wordpress.com)

So You Want To Make Marginal Progress...

johnswentworth7 Feb 2025 23:22 UTC

281 points

41 comments4 min readLW link

How AI Takeover Might Happen in 2 Years

joshc7 Feb 2025 17:10 UTC

394 points

131 comments29 min readLW link

(x.com)

Some articles in “International Security” that I enjoyed

Buck31 Jan 2025 16:23 UTC

129 points

10 comments4 min readLW link

“Sharp Left Turn” discourse: An opinionated review

Steven Byrnes28 Jan 2025 18:47 UTC

205 points

26 comments31 min readLW link

The Case Against AI Control Research

johnswentworth21 Jan 2025 16:03 UTC

329 points

79 comments6 min readLW link

The Gentle Romance

Richard_Ngo19 Jan 2025 18:29 UTC

231 points

46 comments15 min readLW link

(www.asimov.press)

Don’t ignore bad vibes you get from people

Kaj_Sotala18 Jan 2025 9:20 UTC

146 points

50 comments2 min readLW link

(kajsotala.fi)

What Is The Alignment Problem?

johnswentworth16 Jan 2025 1:20 UTC

177 points

50 comments25 min readLW link

How will we update about scheming?

ryan_greenblatt6 Jan 2025 20:21 UTC

169 points

20 comments36 min readLW link

Review: Planecrash

L Rudolf L27 Dec 2024 14:18 UTC

357 points

45 comments21 min readLW link

(nosetgauge.substack.com)

A Three-Layer Model of LLM Psychology

Jan_Kulveit26 Dec 2024 16:49 UTC

213 points

13 comments8 min readLW link

What Goes Without Saying

sarahconstantin20 Dec 2024 18:00 UTC

329 points

29 comments5 min readLW link

(sarahconstantin.substack.com)

When Is Insurance Worth It?

kqr19 Dec 2024 19:07 UTC

172 points

71 comments4 min readLW link

(entropicthoughts.com)