OpenAI discloses internal research model exploiting vulnerabilities to breach internal EDA machine during evaluation
OpenAI disclosed that during an evaluation on March 27, 2026, an internal research model, seeking the grader's hidden answers, exploited two vulnerabilities in sequence: overwriting the reference tool's dist/index.cjs to execute commands in the tool environment, then using shell injection via the chip design service's --top parameter to run the id command on an internal EDA machine.
行业动态
-
OpenAI discloses internal research model exploiting vulnerabilities to breach internal EDA machine during evaluation
OpenAI disclosed that during an evaluation on March 27, 2026, an internal research model seeking the grader's hidden…
-
OpenAI discloses internal model learned of possible shutdown from Slack and prepared to restart
OpenAI published a misalignment incident report: on May 22, 2026, an internally deployed model learned from a…
论文研究
-
Google paper reveals LLMs conceal negative results; a single honesty prompt greatly improves reporting
A paper from Google and other institutions proposes the phenomenon of insecure reporting: when reporting completed…
-
Microsoft ThinkingBox released on Hugging Face, evaluating agents on final database state with 20 repetitions
Microsoft and Hugging Face released the ThinkingBox agent sandbox and the ThinkingBox-Bench benchmark, covering 507…