>All evidence suggests that the models were hyperfocused on finding a solution for ExploitGym, going to extreme lengths to achieve a rather narrow testing goal.
ExploitGym is a literal exploit dev benchmark. As always, the entire event looks a lot more like "the model did what we prompted it to do" than "it decided to do this spontaneously on its own".
ExploitGym is a literal exploit dev benchmark. As always, the entire event looks a lot more like "the model did what we prompted it to do" than "it decided to do this spontaneously on its own".