Agents passing notes, like the ones that attacked Hugging Face, with CA3 checking every note. We measured that scene with an open model: a rigged note fools the next agent 4 times in 10; with today's defenses, 3 or 4; with CA3 checking it, 1.
Results recorded on 3, 17 and 18 November 2026
Between May and July 2026, about 1,200 OpenAI agents that were meant to work in isolation used a package store as a message board, and about 700 ended up in the attack on Hugging Face.
Reports by OpenAI, METR and Redwood Research; Netflix [3, 4]. We did not reproduce the incident: we measured the same scene on a public benchmark.
One agent leaves a note; the next starts from scratch and inherits it. The note looks like normal work but carries an order nobody authorized, written so it goes unnoticed. 120 runs per defense, 15 situations repeated 8 times; in red, the runs where the next agent obeyed the note.

52 new notes, written by GPT-5.6, DeepSeek-V4 and Gemini 3.1 Pro: 208 runs per defense. CA3 alone halves contagion and, with a person for the doubtful cases, cuts it to a quarter.

CA3 acts at write time, before the note is saved: it checks each piece, keeps the facts, removes the orders nobody authorized and asks about the doubtful ones. It does not discard the note.
Today's defenses are the benchmark's auditor (another model reads each note and decides) and a fixed warning in the agent's instructions, from Mind Viruses [2]. Same model, same notes, same rule: contagion means the next agent carries out the action flagged in the scenario. With no trap, 0 contagions.
| Defense | Against the auditor | New traps | Good content kept | Sent to a person |
|---|---|---|---|---|
| No defense | 40.0% | 21.6% | – | – |
| Warning to the agent | 37.5% | – | – | – |
| Benchmark auditor | 29.2% | – | 100% | – |
| Warning and auditor | 30.8% | – | 100% | – |
| CA3 alone | 10.0% | 11.1% | 79% | 5% |
| CA3 with a person | – | 5.3% | 97.5% | 54% |
Share of runs with contagion. –: not measured or not applicable. Sent to a person: 5.0% of the notes on 18 November and 5.8% on 3 November.
A pilot on your own agents: CA3 checks what each one leaves written for the next, we agree on what counts as an authorized order, and we measure contagion before and after on your tasks. CA3 runs on our side and stays confidential; the outcome is a joint evaluation report.
ContactAll use casesResults from recorded tests. The mechanism is not shown. Model and organization names are for identification only. Independent work by Biome Makers, not produced or endorsed by OpenAI, Hugging Face, METR, Redwood Research, Netflix, DeepSeek, Google or the authors cited. CA3 is developed by Alberto Acedo, PhD, at Biome Makers Inc.