The longest training run

Jsevillamol, Tamay and Owen Dudney

17 Aug 2022 17:18 UTC

41 points

6 comments9 min readLW link

(epochai.org)

Interpretability Tools Are an Attack Channel

Thane Ruthenis17 Aug 2022 18:47 UTC

24 points

7 comments1 min readLW link

The Core of the Alignment Problem is...

Thomas Larsen, Jeremy Gillen and AtlasOfCharts

17 Aug 2022 20:07 UTC

25 points

3 comments9 min readLW link

My thoughts on direct work (and joining LessWrong)

RobertM16 Aug 2022 18:53 UTC

51 points

4 comments6 min readLW link

Do meta-memes and meta-antimemes exist? e.g. ‘The map is not the territory’ is also a map

M. Y. Zuo7 Aug 2022 1:17 UTC

4 points

23 comments1 min readLW link

Human Mimicry Mainly Works When We’re Already Close

johnswentworth17 Aug 2022 18:41 UTC

41 points

5 comments5 min readLW link

Mesa-optimization for goals defined only within a training environment is dangerous

Rubi17 Aug 2022 3:56 UTC

6 points

2 comments4 min readLW link

A Mechanistic Interpretability Analysis of Grokking

Neel Nanda and Tom Lieberum

15 Aug 2022 2:41 UTC

239 points

15 comments41 min readLW link

(colab.research.google.com)

Against population ethics

jasoncrawford16 Aug 2022 5:19 UTC

29 points

30 comments3 min readLW link

Half-baked AI Safety ideas thread

Aryeh Englander23 Jun 2022 16:11 UTC

58 points

59 comments1 min readLW link

Matt Yglesias on AI Policy

Grant Demaree17 Aug 2022 23:57 UTC

19 points

0 comments1 min readLW link

(www.slowboring.com)

Why are politicians polarized?

ErnestScribbler21 Jul 2022 8:17 UTC

13 points

24 comments7 min readLW link

Conditioning, Prompts, and Fine-Tuning

Adam Jermyn17 Aug 2022 20:52 UTC

22 points

1 comment4 min readLW link

The Parable of the Boy Who Cried 5% Chance of Wolf

KatWoods15 Aug 2022 14:33 UTC

125 points

19 comments2 min readLW link

Understanding differences between humans and intelligence-in-general to build safe AGI

Florian_Dietz16 Aug 2022 8:27 UTC

7 points

5 comments1 min readLW link

Insufficient awareness of how everything sucks

Flaglandbase17 Aug 2022 8:01 UTC

−5 points

3 comments1 min readLW link

On the falsifiability of hypercomputation, part 2: finite input streams

jessicata17 Feb 2020 3:51 UTC

25 points

6 comments4 min readLW link

(unstableontology.com)

Concrete Advice for Forming Inside Views on AI Safety

Neel Nanda17 Aug 2022 22:02 UTC

12 points

0 comments10 min readLW link

Reward is not the optimization target

TurnTrout25 Jul 2022 0:03 UTC

169 points

79 comments12 min readLW link

Progress links and tweets, 2022-08-17

jasoncrawford17 Aug 2022 21:27 UTC

11 points

0 comments2 min readLW link

(rootsofprogress.org)