Rohin Shah

Karma: 17,372

Research Scientist at Google DeepMind. Creator of the Alignment Newsletter. http://rohinshah.com/

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

86 points

2 comments4 min readLW link

GDM AI Control Roadmap

Mary Phuong, Erik Jenner, Rohin Shah and Seb Farquhar

18 Jun 2026 16:50 UTC

87 points

2 comments1 min readLW link

Testing Gemini models for scheming tendencies

Vika, David Lindner, Seb Farquhar and Rohin Shah

29 May 2026 19:24 UTC

47 points

8 comments6 min readLW link

(deepmindsafetyresearch.medium.com)

GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash

TurnTrout and Rohin Shah

4 Nov 2025 16:25 UTC

55 points

2 comments6 min readLW link

(arxiv.org)

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Tomek Korbak, Mikita Balesni, Vlad Mikulik and Rohin Shah

15 Jul 2025 16:23 UTC

169 points

32 comments1 min readLW link

(bit.ly)

Evaluating and monitoring for AI scheming

Vika, Scott Emmons, Erik Jenner, Mary Phuong, Lewis Ho and Rohin Shah

10 Jul 2025 14:24 UTC

53 points

10 comments5 min readLW link

(deepmindsafetyresearch.medium.com)

Google DeepMind: An Approach to Technical AGI Safety and Security

Rohin Shah5 Apr 2025 22:00 UTC

75 points

12 comments18 min readLW link

(arxiv.org)

Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update #2)

lewis smith, Senthooran Rajamanoharan, Arthur Conmy, CallumMcDougall, Tom Lieberum, János Kramár, Rohin Shah and Neel Nanda

26 Mar 2025 19:07 UTC

117 points

15 comments29 min readLW link

(deepmindsafetyresearch.medium.com)

AGI Safety & Alignment @ Google DeepMind is hiring

Rohin Shah17 Feb 2025 21:11 UTC

103 points

19 comments10 min readLW link

A short course on AGI safety from the GDM Alignment team

Vika and Rohin Shah

14 Feb 2025 15:43 UTC

105 points

2 comments1 min readLW link

(deepmindsafetyresearch.medium.com)

MONA: Managed Myopia with Approval Feedback

Seb Farquhar, David Lindner and Rohin Shah

23 Jan 2025 12:24 UTC

81 points

30 comments9 min readLW link

AGI Safety and Alignment at Google DeepMind: A Summary of Recent Work

Rohin Shah, Seb Farquhar and Anca Dragan

20 Aug 2024 16:22 UTC

217 points

33 comments9 min readLW link

On scalable oversight with weak LLMs judging strong LLMs

zac_kenton, Noah Siegel, janos, Jonah Brown-Cohen, Samuel Albanie, David Lindner and Rohin Shah

8 Jul 2024 8:59 UTC

49 points

18 comments7 min readLW link

(arxiv.org)

Improving Dictionary Learning with Gated Sparse Autoencoders

Senthooran Rajamanoharan, Arthur Conmy, lewis smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah and Neel Nanda

25 Apr 2024 18:43 UTC

63 points

38 comments1 min readLW link

(arxiv.org)

AtP*: An efficient and scalable method for localizing LLM behaviour to components

Neel Nanda, János Kramár, Tom Lieberum and Rohin Shah

18 Mar 2024 17:28 UTC

19 points

0 comments1 min readLW link

(arxiv.org)

Fact Finding: Do Early Layers Specialise in Local Processing? (Post 5)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

18 points

3 comments4 min readLW link

Fact Finding: How to Think About Interpreting Memorisation (Post 4)

Senthooran Rajamanoharan, Neel Nanda, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

24 points

0 comments9 min readLW link

Fact Finding: Trying to Mechanistically Understanding Early MLPs (Post 3)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:46 UTC

12 points

1 comment16 min readLW link

Fact Finding: Simplifying the Circuit (Post 2)

Senthooran Rajamanoharan, Neel Nanda, János Kramár and Rohin Shah

23 Dec 2023 2:45 UTC

27 points

3 comments14 min readLW link

Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1)

Neel Nanda, Senthooran Rajamanoharan, János Kramár and Rohin Shah

23 Dec 2023 2:44 UTC

109 points

12 comments22 min readLW link 2 reviews