BREAKING: Dwarkesh spent $20k in API credits to make frontier models play Blood on the…
This is a AI post classified by AGK Intelligence as AI agents (a model release), kept by the AI Radar because it carries real work, not commentary.
BREAKING: Dwarkesh spent $20k in API credits to make frontier models play Blood on the Clocktower against each other. 386 games. Hidden roles, bluffing, and a demon that has to scheme with its team. Astra came out roughly 430 Elo above Opus 4.6, winning about 92% of that matchup. The capability on display is multi-agent scheming. The sharper skill is epistemic hygiene: not treating one corrupted clue as a full clear on a player. Full results are on http://clocktowerbench.com, and the native 18 minute video walks through the games. If you build agents that coordinate with other agents, how
Posted by Guillermo Flor (14k followers) 14 h ago · 1 likes · 516 views · view the original post on X. Kept by the AI Radar as AI agents. Tools mentioned: clocktowerbench.com.
More AI work like this
- this week at langchain: — @hwchase17
- Get @bot - it will change your life. Then add the open Longevity Grok and it will work… — @biogerontology
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- I asked what the oldest or weirdest device talking to your Hermes Agent is. my favorites: — @witcheer
- Have two agents doing a thorough code review of the new Hermes Agent Templates to ensure… — @MichaelGannotti
- Your AI agent needs to browse the web. Does it need a full Chromium instance to do it? — @mr_r0b0t
- Copy a WordPress contact page from an old site and its SiteOrigin form still sends to… — @johnturner
- Tobira turns your website into an agent that sells to your customer's AI inside ChatGPT… — @ProductHunt
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.