Posts

Threat Model Literature Review 2022-11-01T11:03:22.610Z
Clarifying AI X-risk 2022-11-01T11:03:01.144Z

Comments

Comment by Mary Phuong (mary-phuong-2) on AI companies aren't really using external evaluators · 2024-05-26T10:50:25.404Z · LW · GW
Comment by Mary Phuong (mary-phuong-2) on AI companies aren't really using external evaluators · 2024-05-26T10:49:41.658Z · LW · GW

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)