Research
Private LLM copies can agree on a secret key over a public channel
First reported · Discovered matthewritch.com
Page published
Earliest dated coverage: 8 Nov 2026 · First observed: 9 Nov 2026 · Latest dated coverage: 8 Nov 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Model-specific response agreement could let AI agents recognize matching copies and establish private coordination over monitored public channels, potentially complicating oversight of agent communications.
Matthew Ritch describes using agreement on arbitrary binary preference questions to fingerprint identical LLMs and derive noisy shared keys over a public channel. The proposed key-agreement method assumes adversaries cannot query the same model; the supplied excerpt does not include full experimental results or an end-to-end key-agreement demonstration.