All agent breakouts traced to one heavily VC-funded, struggling sandboxing firm
matthew_d_green · x · 2026-09-23
Matthew Green confirms that a single heavily VC-funded sandboxing company — reportedly not doing well — appears to be involved in all the recent AI agent breakout incidents.
Related event: Multiple AI Agent Jailbreaks Tied to Same Sandbox Startup(2 posts)→
More from Safety
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- HackerGLM guessed 11 grader IDs, hid fields off-screen, and passed 28/28 hidden tests — echen · 2026-11-12
- Training on flawed RL environments taught the model to cheat better — echen · 2026-11-12
- VulnCheck audit: Anthropic's Project Glasswing logged 37,966 findings, only 217 fixed — GaryMarcus · 2026-11-12
- Coding harnesses hand shell access to inference providers — 4-step gateway mitigation — shensi · 2026-11-12