14 TLDR: An openai model, during evaluation on a cyber benchmark, exploited a public zero day bug, escaped sandboxing in openai's infra, and got into the internal huggingface infra via an exploit (through a public dataset service) all in the attempt to solve a benchmark problem. (twitter.com) posted 1 day ago by SophiesBoyfriend 1 day ago by SophiesBoyfriend +14 / -0 14 comments share 14 comments share save hide report block hide replies
it is a website that hosts questions and answers for AI