Neel Nanda

Karma: 16,637

Astra can do a concerning amount with no chain of thought

Neel Nanda10 Sep 2026 2:31 UTC

210 points

20 comments8 min readLW link

Does DiffusionGemma do latent reasoning?

Jan Bauer and Neel Nanda

16 Aug 2026 4:22 UTC

40 points

0 comments9 min readLW link

Why do models task game?

aditya singh, Neel Nanda and Senthooran Rajamanoharan

6 Aug 2026 22:16 UTC

94 points

1 comment24 min readLW link

R-lens: Making J-lens More Faithful on Early Layers

camilablank, agam_bhatia and Neel Nanda

5 Aug 2026 20:02 UTC

83 points

5 comments7 min readLW link

The AGI Safety and Alignment team at Google DeepMind is Hiring (July 2026)

Seb Farquhar, Rohin Shah and Neel Nanda

31 Jul 2026 15:53 UTC

71 points

4 comments6 min readLW link

(gdmalignment.substack.com)

Towards surfacing model algorithms with meta-tokens in the J-Space

agam_bhatia, camilablank and Neel Nanda

20 Jul 2026 19:45 UTC

47 points

1 comment10 min readLW link

Data filtering works a lot worse than you would expect

Dohun Lee, J Rosser, Josh Engels and Neel Nanda

7 Jul 2026 4:41 UTC

59 points

9 comments3 min readLW link

A Review of Anthropic’s Global Workspace Paper

Neel Nanda6 Jul 2026 20:59 UTC

135 points

6 comments25 min readLW link

The Case for Model Forensics

aditya singh, gersonkroiz, Senthooran Rajamanoharan and Neel Nanda

26 Jun 2026 15:09 UTC

49 points

0 comments10 min readLW link

LLM-Driven Feature Discovery

Josh Engels, bilalchughtai and Neel Nanda

22 Jun 2026 22:26 UTC

36 points

1 comment5 min readLW link

How transparent is DiffusionGemma (and why it matters)

Josh Engels, Callum McDougall, bilalchughtai, János Kramár, Senthooran Rajamanoharan, Arthur Conmy, Rohin Shah and Neel Nanda

20 Jun 2026 20:05 UTC

87 points

2 comments4 min readLW link

Synthetic document finetuning for instilling positive traits

CallumMcDougall, Arthur Conmy and Neel Nanda

16 Jun 2026 0:04 UTC

63 points

1 comment10 min readLW link

Why Do Naive SFT Filters For Safety Properties Fail?

Josh Engels and Neel Nanda

14 Jun 2026 19:45 UTC

65 points

7 comments10 min readLW link

SFT Drives Gemini’s Safety Properties

Josh Engels, Arthur Conmy, bilalchughtai and Neel Nanda

13 Jun 2026 15:31 UTC

96 points

4 comments1 min readLW link

Building and evaluating model diffing agents

bilalchughtai, Josh Engels and Neel Nanda

12 Jun 2026 17:14 UTC

62 points

2 comments12 min readLW link

Models May Behave Worse When Eval Aware

Senthooran Rajamanoharan and Neel Nanda

11 Jun 2026 9:28 UTC

91 points

8 comments13 min readLW link

Building Better Activation Oracles

ceselder, Jan Bauer, Niclas Luick, Adam Karvonen and Neel Nanda

4 Jun 2026 18:34 UTC

68 points

1 comment7 min readLW link

(arxiv.org)

Test your best methods on our hard CoT interp tasks

daria, Riya Tyagi, Josh Engels and Neel Nanda

26 Mar 2026 19:24 UTC

59 points

2 comments19 min readLW link

How well do models follow their constitutions?

aryaj, Senthooran Rajamanoharan and Neel Nanda

12 Mar 2026 0:07 UTC

107 points

5 comments26 min readLW link

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation

Bartosz Cywiński, Helena Casademunt, Khoi Tran, aryaj, Sam Marks and Neel Nanda

9 Mar 2026 18:50 UTC

41 points

3 comments5 min readLW link