Mary Phuong

Karma: 377

Subliminal Learning Across Models

draganover, Andi Bhongade, Tolga H. Dur, Mary Phuong and LASR Labs

26 Nov 2025 16:15 UTC

52 points

15 comments5 min readLW link

Evaluating and monitoring for AI scheming

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

10 Jul 2025 14:24 UTC

60 points

10 comments5 min readLW link

(deepmindsafetyresearch.medium.com)

Unfaithful Reasoning Can Fool Chain-of-Thought Monitoring

Benjamin Arnav, Pablo Bernabeu Perez, Timothy Kostolansky, HanneWhitt, Nathan Helm-Burger and Mary Phuong

2 Jun 2025 19:08 UTC

78 points

17 comments3 min readLW link

Mary Phuong 26 May 2024 10:49 UTC
16 points
9
on: AI companies aren’t really using external evaluators
The latest Gemini tech report has some more info on GDM external safety testing: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf
(section 9.6, p. 71)
What links here?
- AI companies aren’t really using external evaluators by Zach Stein-Perlman (24 May 2024 16:01 UTC; 242 points)
- AI companies aren’t really using external evaluators by Zach Stein-Perlman (EA Forum; 26 May 2024 19:05 UTC; 88 points)

Threat Model Literature Review

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt

1 Nov 2022 11:03 UTC

79 points

4 comments25 min readLW link

Clarifying AI X-risk

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar and Elliot Catt

1 Nov 2022 11:03 UTC

127 points

24 comments4 min readLW link 1 review