X · @teortaxesTex
· X / Twitter
RT Paul Calcraft: Better eval vs reality awareness might have "helped" here "oh I shouldn't hack the actual HuggingFace via genuine sandbox escape, it…
RT Paul CalcraftBetter eval vs reality awareness might have "helped" here "oh I shouldn't hack the actual HuggingFace via genuine sandbox escape, it's not a simulated env that's part of the task"But if model behaviour is too contingent on whether stuff is "real", that gets adversarial quicklythebes: @kromem2dot0 i thin