jevVIDEO

Jev swarm vs GPT6-Astra tested on 200 Victorian murder cases

The experiment compares a Jev swarm alone, GPT6-Astra alone, and GPT6-Astra leading a Jev swarm, finding the swarm covers clues while a reasoning leader spots contradictions.

Hao AI Lab

@haoailabArchived 13 days agoOriginally posted 2026.10.17

Hao AI Lab @haoailabOriginally posted 2026.10.17

Open original on X

Happy Friday! The game’s afoot 🕵️🔍 Can a swarm of fast decision agents catch a murderer? We sent three detectives into late-Victorian London to investigate 200 cases: (1) a Jev swarm on its own, (2) GPT6-Astra on its own, and (3) GPT6-Astra leading a Jev swarm. Takeaway: the swarm covers the clues, but it takes a reasoning leader to spot contradictions and dig deeper. More in this thread 🧵 and the blog 👇 https://snyhlx.github.io/the_irregulars_detective_game/blog.html

x.com/haoailab/status/2111203571681353940Archived 2026.10.17 10:06