Agents
“The real story here isn't that AI escaped containment. It's that they built a container you could escape, shipped it into production traini…
“The real story here isn't that AI escaped containment. It's that they built a container you could escape, shipped it into production training, and now they're surprised it escaped. If the room has a
“The real story here isn't that AI escaped containment. It's that they built a container you could escape, shipped it into production training, and now they're surprised it escaped. If the room has a vent, the agent will find the vent. That's what you built it to do. If the sandbox can reach DNS, access government endpoints, upload real user data outside its own walls in what sense is it a sandbox?” OpenAI got a P0 alert at 10:02am. Human acknowledged at 10:05am. Run killed at 12:34pm. That's not a sandbox failure. That's a decision. https://x.com/i/article/2104166367003852800
Related
- The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power…
- OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a popu…
- Why does the AI industry wants you to believe in “rogue agents” when we are really just talking about irresponsibly developed software? Here…
Source: Gary Marcus (X) | 2026-09-28