Comment by ls612
19 hours ago
I mean they say they will release the weights by November 4, so presumably after that it won’t be hard for people to fine-tune it to be better at cyber right?
19 hours ago
I mean they say they will release the weights by November 4, so presumably after that it won’t be hard for people to fine-tune it to be better at cyber right?
My understanding is if something is entirely absent from the dataset, good luck trying to teach a model that through post training
Given that most of their improvements here are positioned as RL on their last base train, seems like just doing some additional RL would work fine?
Presumably if it knows how to find and fix bugs it can be told how to exploit them. But who knows what it will actually be capable of doing in the real world as opposed to Kiki’s benchmarks