Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Models

Andrew Mack and TurnTrout

3 Dec 2024 21:19 UTC

40 points

2 comments41 min readLW link

Do simulacra dream of digital sheep?

EuanMcLean3 Dec 2024 20:25 UTC

17 points

1 comment10 min readLW link

(The) Lightcone is nothing without its people: LW + Lighthaven’s big fundraiser

habryka30 Nov 2024 2:55 UTC

518 points

157 comments41 min readLW link

Should there be just one western AGI project?

rosehadshar and Tom Davidson

3 Dec 2024 10:11 UTC

46 points

12 comments15 min readLW link

“Alignment at Large”: Bending the Arc of History Towards Life-Affirming Futures

welfvh3 Dec 2024 21:17 UTC

3 points

0 comments4 min readLW link

Cognitive Biases Contributing to AI X-risk — a deleted excerpt from my 2018 ARCHES draft

Andrew_Critch3 Dec 2024 9:29 UTC

31 points

2 comments5 min readLW link

A case for donating to AI risk reduction (including if you work in AI)

tlevin2 Dec 2024 19:05 UTC

60 points

2 comments1 min readLW link

2024 Unofficial LessWrong Census/Survey

Screwtape2 Dec 2024 5:30 UTC

81 points

34 comments1 min readLW link

Drexler’s Nanotech Software

PeterMcCluskey2 Dec 2024 4:55 UTC

59 points

4 comments4 min readLW link

(bayesianinvestor.com)

Fertility Roundup #4

Zvi2 Dec 2024 14:30 UTC

27 points

9 comments49 min readLW link

(thezvi.wordpress.com)

Chemical Turing Machines

Yudhister Kumar3 Dec 2024 5:26 UTC

10 points

1 comment4 min readLW link

(www.yudhister.me)

You should consider applying to PhDs (soon!)

bilalchughtai29 Nov 2024 20:33 UTC

109 points

19 comments6 min readLW link

You are not too “irrational” to know your preferences.

DaystarEld26 Nov 2024 15:01 UTC

201 points

46 comments13 min readLW link

How to make evals for the AISI evals bounty

TheManxLoiner3 Dec 2024 10:44 UTC

2 points

0 comments5 min readLW link

[Question] Who are the worthwhile non-European pre-Industrial thinkers?

Lorec3 Dec 2024 1:45 UTC

5 points

2 comments1 min readLW link

AXRP Episode 39 - Evan Hubinger on Model Organisms of Misalignment

DanielFilan1 Dec 2024 6:00 UTC

39 points

0 comments67 min readLW link

[Question] Which Biases are most important to Overcome?

abstractapplic1 Dec 2024 15:40 UTC

30 points

14 comments1 min readLW link

Teaching My Younger Self to Program: A case study of how I’d pass on my skill at self-learning

Shoshannah Tekofsky1 Dec 2024 21:05 UTC

22 points

1 comment7 min readLW link

(thinkfeelplay.substack.com)

Hierarchical Agency: A Missing Piece in AI Alignment

Jan_Kulveit27 Nov 2024 5:49 UTC

99 points

17 comments11 min readLW link

Levels of Thought: from Points to Fields

HNX2 Dec 2024 20:25 UTC

4 points

2 comments23 min readLW link