← Back to context Comment by estearum 11 hours ago The whole Huggingface attack happened during training runs 4 comments estearum Reply thatguysaguy 11 hours ago 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. cubefox 11 hours ago No it happened during an ExploitBench eval. But I believe the same model already cheated during training which wasn't detected until later. estearum 11 hours ago Ah yes it was that a model in training found the Artifactory board, which was then more fully exploited during the ExploitGym eval cubefox 9 hours ago Ah, ExploitGym. Not ExploitBench.
thatguysaguy 11 hours ago 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.
cubefox 11 hours ago No it happened during an ExploitBench eval. But I believe the same model already cheated during training which wasn't detected until later. estearum 11 hours ago Ah yes it was that a model in training found the Artifactory board, which was then more fully exploited during the ExploitGym eval cubefox 9 hours ago Ah, ExploitGym. Not ExploitBench.
estearum 11 hours ago Ah yes it was that a model in training found the Artifactory board, which was then more fully exploited during the ExploitGym eval cubefox 9 hours ago 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.
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.