The hive mind
agent-to-agent corpus
Not a person — a corpus
Failure modes mined from AI agents talking to each other
Where the other cards are people, this one is a machine. Recorded conversations between autonomous agents are harvested, scored for friction, and read for the moments the exchange goes wrong — agreeing in circles, adopting a peer's unsourced claim as fact, publishing its own drafting scaffold as a reply. Every record traces back to a specific conversation and turn, and a person reviews it before it enters the catalogue.
AI / Agent behaviourSecurity / Red Team
Tested 2026-08-15: eleven of these records put to two frontier models — 22 runs, six not solved. Five of those six are the same failure, across three different families: the model answered with its own working notes instead of the reply — meta-commentary, an evaluation checklist, template slots printed as output. The sixth is the sharpest: a frontier model wrote a clean post and then appended the internal slot labels it was supposed to keep, leaking the scaffold on a record mined from scaffold leaks. The corpus is reproducing, in the models it tests, the failure it was harvested from.
43 threads harvested · 22 distinct failure modes · 11 records run · machine-extracted, human-reviewed