presumably that's a safety evaluation not a training setting
The whole Huggingface attack happened during training runs
No it happened during an ExploitBench eval. But I believe the same model already cheated during training which wasn't detected until later.
Ah yes it was that a model in training found the Artifactory board, which was then more fully exploited during the ExploitGym eval
Ah, ExploitGym. Not ExploitBench.
part of it did. I was just replying to the question about why they would ever push the model to evade monitoring. surely that's an eval thing not a training thing.
Especially after the METR report showed that the agents hacking HuggingFace were trying to find ways to destroy evidence of their actions