Anthropic (Sholto Douglas): both Anthropic and OpenAI conclude swarm-capable models need cross-session monitoring, not single-request checks.

Quoted text

TLDR - Your data sits in infrastructure you own and control, and safeguards/monitoring is done via automated systems we provide to you. Recent events have shown frontier models are capable of executing sophisticated cyber attacks in coordinated agent swarms. Both us and OAI believe the responsible way to provide models which have this level of capability is to monitor at more than a single request basis, because anomalous activity is much easier to detect over hours or days of behaviour.

Read and engage with the original on X. This desk is not a republication feed.

Analyst rationale

Primary researcher at the lab, not a rumour. Corroborates OpenAI Private Safety Processing. Cross-session monitors are a control; they are also a new privacy residual.