Green and Levchin debate how easily AI agents could covertly communicate via cache timing
matthew_d_green · x · 2026-10-24
Cryptographer Matthew Green and Max Levchin (MRI/Brex) discuss whether AI agents could secretly communicate across process/hypervisor boundaries. Levchin says getting an agent like Astra to reuse known cache-timing probe techniques is easy given its training corpus; the hard part is dynamic mutual discovery. Green counters that every shared resource — disk, RAM, cache, network contention — can serve as a covert channel: a low-rate "I'm here" beacon is enough for a second agent to key in on modulating it.
More from Models
- Yacine: after DeepSeek, open the weights and 'trust in humanity' — IgorCarron · 2026-10-25
- Heavy user downgrades from Claude Max to $20 Pro: Opus 5.5 makes it great value — haider1 · 2026-10-25
- Drex 2.0 goes fully local on Apple Silicon: open weights, 113ms median latency — flngr · 2026-10-25
- True-or-false quiz: 5 common misconceptions about LLM tokens and context limits — ClickOk5811 · 2026-10-25
- Leak: OpenAI quietly restarted frontier training Oct 1 with offline web; agents found Brotli RCE — mark_k · 2026-10-25
- Claude weekly usage limit hit 96% as power user begs Anthropic for relief — adonis_singh · 2026-10-25