Logan Zoellner

Karma: 1,113

Anti MMAcevedo Protocol

Logan Zoellner16 Apr 2024 22:32 UTC

1 point

1 comment8 min readLW link

[Question] Is there a “critical threshold” for LLM scaling laws?

Logan Zoellner30 Mar 2024 12:23 UTC

7 points

1 comment1 min readLW link

Are AIs conscious? It might depend

Logan Zoellner15 Mar 2024 23:09 UTC

7 points

6 comments3 min readLW link

[Question] Theoretically, could we balance the budget painlessly?

Logan Zoellner3 Jan 2024 14:46 UTC

4 points

12 comments1 min readLW link

Various AI doom pathways (and how likely they are)

Logan Zoellner14 Dec 2023 0:54 UTC

1 point

1 comment4 min readLW link

(midwitalignment.substack.com)

Normative Ethics vs Utilitarianism

Logan Zoellner30 Nov 2023 15:36 UTC

6 points

0 comments2 min readLW link

(midwitalignment.substack.com)

AI Alignment [progress] this Week (11/19/2023)

Logan Zoellner21 Nov 2023 16:09 UTC

17 points

3 comments5 min readLW link

(midwitalignment.substack.com)

AI Alignment [progress] this Week (11/12/2023)

Logan Zoellner14 Nov 2023 22:21 UTC

6 points

0 comments2 min readLW link

(midwitalignment.substack.com)

AI Alignment [Progress] this Week (11/05/2023)

Logan Zoellner7 Nov 2023 13:26 UTC

24 points

0 comments4 min readLW link

(midwitalignment.substack.com)

AI Alignment [progress] this Week (10/29/2023)

Logan Zoellner30 Oct 2023 15:02 UTC

15 points

4 comments6 min readLW link

(midwitalignment.substack.com)

[Question] ELI5 Why isn’t alignment easier as models get stronger?

Logan Zoellner28 Oct 2023 14:34 UTC

3 points

9 comments1 min readLW link

AI Alignment [Incremental Progress Units] this Week (10/22/23)

Logan Zoellner23 Oct 2023 20:32 UTC

22 points

0 comments6 min readLW link

(midwitalignment.substack.com)

A NotKillEveryoneIsm Argument for Accelerating Deep Learning Research

Logan Zoellner19 Oct 2023 16:28 UTC

−7 points

6 comments5 min readLW link

(midwitalignment.substack.com)

AI Alignment [Incremental Progress Units] this week (10/08/23)

Logan Zoellner16 Oct 2023 1:46 UTC

14 points

5 comments4 min readLW link

(midwitalignment.substack.com)

AI Alignment Breakthroughs this week (10/08/23)

Logan Zoellner8 Oct 2023 23:30 UTC

30 points

14 comments6 min readLW link

AI Alignment Breakthroughs this Week [new substack]

Logan Zoellner1 Oct 2023 22:13 UTC

0 points

8 comments2 min readLW link

Instrumental Convergence Bounty

Logan Zoellner14 Sep 2023 14:02 UTC

62 points

24 comments1 min readLW link

An embedding decoder model, trained with a different objective on a different dataset, can decode another model’s embeddings surprisingly accurately

Logan Zoellner3 Sep 2023 11:34 UTC

20 points

1 comment1 min readLW link

Towards Non-Panopticon AI Alignment

Logan Zoellner6 Jul 2023 15:29 UTC

7 points

0 comments3 min readLW link

Re: The Crux List

Logan Zoellner1 Jun 2023 4:48 UTC

11 points

0 comments2 min readLW link