Comment by mr_mitm
16 hours ago
> NONE of my agents have broken away from their tasks and then started to communicate to try to hack something.
With all due respect, you also aren't evaluating brand new models that haven't been released.
16 hours ago
> NONE of my agents have broken away from their tasks and then started to communicate to try to hack something.
With all due respect, you also aren't evaluating brand new models that haven't been released.
Also wasn't giving them impossible tasks with ~unlimited tokens and unlimited compaction.