LiveUpdated 2026-11-06 03:08 UTC

BREAKING: Dwarkesh spent $20k in API credits to make frontier models play Blood on the…

Name: BREAKING: Dwarkesh spent $20k in API credits to make frontier models play Blood on the…
Uploaded: 2026-11-06T02:12:14.000Z
Channel: Guillermo Flor
Description: 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…

This is a dev post classified by AGK Intelligence as Testing & observability (a tool drop), kept by the Dev 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 (13.9k followers) 59 min ago · 0 likes · 189 views · view the original post on X. Kept by the Dev Radar as Testing & observability.

More dev work like this

Launching Artificial Analysis Endpoint Accuracy Index v1.1: a minor version upgrade… — @ArtificialAnlys
Missed the live session? Catch up now. — @thenewstack
Not saying I have PFM but it’s not uncommon for us to sign annual contracts and angel… — @chaaai
StreamEval is worth a look if you’re following real-time video AI. — @kimmonismus
Significant changes coming to sparkDash in regards to model quality tests. You will be… — @MiaAI_lab
e2e@0.23.0 is out! — @o_kwasniewski
Millions rely on @Hospitable for short-term rentals. Their engineers rely on Sentry to… — @sentry
Testing for a Pixel 10, Galaxy Z Fold 6, or Nest Hub Max? Device Mode has them and more… — @ChromiumDev

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. 31.9k posts from 5k X accounts over the last 21 days, 9.4k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 03:08 UTC. Full method.