Joe Benton(@JoeJBenton):📄 As AI systems get increasingly powerful, it might be very important that they can help with key tasks like AI safety research. I think TASTE, this eval which @hasanbaig8 painstakingly built, may be one of the best signals of whether we're on track for our AIs to be helpful.

Joe Benton

@JoeJBenton

Soon joining @METR_Evals | Previously Alignment at Anthropic, PhD at University of Oxford

参加 February 2017

63 フォロー中 13.1K ファン

Joe Benton@JoeJBenton

2026.09.07 16:27

📄 As AI systems get increasingly powerful, it might be very important that they can help with key tasks like AI safety research. I think TASTE, this eval which @hasanbaig8 painstakingly built, may be one of the best signals of whether we're on track for our AIs to be helpful.

Hasan@hasanbaig8

2026.08.29 17:14

As we increasingly automate AI R&D, can we also automate AI Safety research? We built TASTE (The AI Safety Taste Evaluation), a benchmark to measure whether models can predict which research proposals experienced AI safety researchers prefer.