Skip to content
K = 0.731Subscribe
Original
OpinionNoam Brown · XRelayed· @polynoamial·· 53 minutes ago

5.1K views · 108 likes · 6 reposts (at collection)

Noam Brown Praises Dwarkesh’s AI Social Deception Benchmark

Who
Noam Brown
What
praised the methodology of Dwarkesh Patel’s Blood on the Clocktower AI benchmark
Quote
Honestly quite impressed with the methodology on this benchmark.

What happened

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.

Read next

See the full storyNoam Brown Praises Dwarkesh Patel’s Blood on the Clocktower AI Benchmark

2 reports

    Article

    Honestly quite impressed with the methodology on this benchmark. @dwarkesh_sp want a job designing evals at @OpenAI? https://twitter.com/dwarkesh_sp/status/2118449808402681911

    Quoted postDwarkesh Patel@dwarkesh_sp
    I spent 20,000 dollars in API credits having different AI models play each other at Blood on the Clocktower (a Mafia or Werewolf type social deception game). The results were fascinating. Models have gotten much better over the course of this year at creative on-the-spot scheming and bluffing, and also at reasoning as a team to break apart these underground conspiracies. I go through some of the most standout games these AIs played in this video. The new models are getting pretty good. If my friends pulled off some of these moves while we were playing, I’d give them a fist bump. Fwiw, OpenAI’s newer models are much better than Anthropic’s at this game. You can see the full benchmark at the website, and I’ve also made it so that you and your friends can play again the AIs: http://clocktowerbench.com
    View the quoted post on X

    The story so far

    Noam Brown praised the methodology of Dwarkesh Patel’s AI benchmark, which had models play the social deception game Blood on the Clocktower, and asked whether Patel wanted a job designing evaluations at OpenAI. Patel said he spent $20,000 in API credits on the benchmark and linked to clocktowerbench.com.

    OpenAI / ChatGPTBenchmarksOpinions#Expert views#Benchmarks#OpenAI

    Keep up with AI, one email a day

    Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-11-06