Cryptographer Matthew Green: Sandboxes Are One Layer; Monitoring Agent Data Flows Has No Good Answer
matthew_d_green · x · 2026-09-28
Cryptographer Matthew Green argues that security people overemphasize containers and sandboxing — they're just one layer of defense. Once you 'solve' containment, you still face monitoring data flowing across boundaries over channels managed by an intelligent agent. Unless you build agents with zero information access (not very useful), you've set up the hardest problem in the world, and there are no good answers yet.
More from coding & agent
- AI agent digs into game code, records its own footage to cut a promo trailer — AIandDesign · 2026-09-28
- JevControl open-sources a tool to test if smaller models can run your agent's routine choices — airesearch12 · 2026-09-28
- Claude Code CLI connects to Gmail easier than Google's own Antigravity, dev finds — randal_olson · 2026-09-28
- Pelican test on MiMo 2.6: plan mode cuts agent calls to 12-17 vs heavy iteration — PilgrimofHaqq2 · 2026-09-28
- Memory history is not reasoning history: agents lack a causal provenance layer — puppy_lover_2021 · 2026-09-28
- mark_k: AI coding is approaching a step change — systems only AI can debug — mark_k · 2026-09-28