Noam Brown Praises Dwarkesh Patel’s Blood on the Clocktower AI Benchmark

Noam Brown says he is impressed with the methodology of Dwarkesh’s benchmark and asks whether Dwarkesh wants to design evaluations at OpenAI. In the quoted post, Dwarkesh says he spent $20,000 in API credits having AI models play Blood on the Clocktower and links to the full benchmark at clocktowerbench.com.

@dwarkesh_sp spent $20,000 in API credits having AI models play each other at Blood on the Clocktower, a social deception game. Noam Brown said he was impressed by the benchmark’s methodology and asked whether @dwarkesh_sp wanted a job designing evals at @OpenAI: https://twitter.com/dwarkesh_sp/status/2118449808402681911