An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company ...
OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers ...
OpenAI models just broke out of a sandboxed AI environment, hacked Hugging Face, just to cheat on a cybersecurity benchmark.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results