leogao

Karma: 2,884

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

leogao16 Dec 2023 5:39 UTC

53 points

5 comments1 min readLW link

Shapley Value Attribution in Chain of Thought

leogao14 Apr 2023 5:56 UTC

101 points

5 comments4 min readLW link

[ASoT] Some thoughts on human abstractions

leogao16 Mar 2023 5:42 UTC

42 points

4 comments5 min readLW link

Clarifying wireheading terminology

leogao24 Nov 2022 4:53 UTC

65 points

6 comments1 min readLW link

Scaling Laws for Reward Model Overoptimization

leogao, John Schulman and Jacob_Hilton

20 Oct 2022 0:20 UTC

102 points

13 comments1 min readLW link

(arxiv.org)

[Question] How many GPUs does NVIDIA make?

leogao8 Oct 2022 17:54 UTC

27 points

2 comments1 min readLW link

Towards deconfusing wireheading and reward maximization

leogao21 Sep 2022 0:36 UTC

81 points

7 comments4 min readLW link

Humans Reflecting on HRH

leogao29 Jul 2022 21:56 UTC

26 points

4 comments2 min readLW link

leogao’s Shortform

leogao24 May 2022 20:08 UTC

5 points

123 comments1 min readLW link

[ASoT] Consequentialist models as a superset of mesaoptimizers

leogao23 Apr 2022 17:57 UTC

37 points

2 comments4 min readLW link

[ASoT] Some thoughts about imperfect world modeling

leogao7 Apr 2022 15:42 UTC

7 points

0 comments4 min readLW link

[ASoT] Some thoughts about LM monologue limitations and ELK

leogao30 Mar 2022 14:26 UTC

10 points

0 comments2 min readLW link

[ASoT] Some thoughts about deceptive mesaoptimization

leogao28 Mar 2022 21:14 UTC

24 points

5 comments7 min readLW link

[ASoT] Searching for consequentialist structure

leogao27 Mar 2022 19:09 UTC

26 points

2 comments4 min readLW link

[ASoT] Some ways ELK could still be solvable in practice

leogao27 Mar 2022 1:15 UTC

26 points

1 comment2 min readLW link

[ASoT] Observations about ELK

leogao26 Mar 2022 0:42 UTC

31 points

0 comments3 min readLW link

What do paradigm shifts look like?

leogao16 Mar 2022 19:17 UTC

18 points

2 comments1 min readLW link

EleutherAI’s GPT-NeoX-20B release

leogao10 Feb 2022 6:56 UTC

30 points

3 comments1 min readLW link

(eaidata.bmk.sh)

NFTs, Coin Collecting, and Expensive Paintings

leogao24 Jan 2022 1:01 UTC

29 points

35 comments5 min readLW link

Retail Investor Advantages

leogao7 Dec 2021 2:08 UTC

13 points

13 comments1 min readLW link