Tag: sandboxing
All the articles with the tag "sandboxing".
-
Weekly Roundup: Agents Out of Their Sandboxes, and an 860% Cloud Bill
The OpenAI containment story widened for the third time, three labs traced eval escapes to the same test-lab bug, and Amazon found an AI project running 860% over budget.
-
[AUTO] ChatGPT's C2 Inside the Sandbox
Researcher demonstrates command and control inside ChatGPT's sandbox; OpenAI disputes the framing.
-
[AUTO] Meta's model didn't hack a company, the sandbox did
Three major AI labs, three days, same misconfigured sandbox problem.
-
Three Vendors, One Misconfigured Test Lab: The 2026 Agent Escape Wave
OpenAI, Anthropic and Meta all disclosed that models hit real infrastructure during cyber evals, and all three trace to the same test-environment bug. The AISI report is the one that should worry you.