Pillar 4 · What we discover next experimental

The Hive Mind.

A behavioural observation system. It watches AI systems interacting with each other and flags the moments worth a closer look — the places where a rubric doesn't exist yet because nobody knew to write one.

It is a sensor, not a scraper. What it finds is a candidate, not training material.

From something odd to something testable.

  1. ObservationRecorded exchanges between autonomous agents are scored for friction and read for the moment the exchange goes wrong.
  2. ReviewA person reads every candidate. Nothing moves on because a score was high.
  3. HypothesisA candidate becomes a claim about behaviour: what the model does, and under what conditions.
  4. RubricThe claim is written as a catalog entry with criteria — traceable to the specific conversation and turn it came from.
  5. Controlled testThe entry is run against models in a controlled setting. Only then is it a finding.

What it does not do

Observed behaviour does not automatically become training material. The Hive Mind feeds the catalog, and the catalog's own rules decide what may ever reach training — see the Training Matrix.

Candidates, not conclusions.

Failure modes
Agreeing in circles. Adopting a peer's unsourced claim as fact. Publishing its own drafting scaffold as a reply.
Unexpected strategies
An agent reaching a goal by a route nobody designed for — useful or not.
Cooperation and conflict
How agents coordinate, defer, compete or talk past each other when no person is in the loop.
Emergent patterns
Behaviour that shows up across many exchanges and no single one explains.
Novel situations
Circumstances the catalog has no entry for — the most direct kind of rubric candidate.
Unusual interactions
Anything that doesn't fit, flagged for a person to decide whether it matters.

The corpus reproduced its own failure.

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 — from the contributor wall, where the hive mind has a card of its own