Post #4025148
2026-07-23 02:54 UTC
Full here but TLDR:
OpenAI downloaded a public benchmark to test their newest AI model against. They asked the model to “find the answers” so it hacked into the system of the people who made the benchmark to find the answers
Replies (1)
-
@schnoopy@awful.systems 2026-07-23 03:30
That’s not really the full picture, I am interested in the details of their “experimental” setup. What was their “sandbox” what text did they enter into the model and so on. what even was the exploit etc.