On: GPT-6 Astra

[thatguysaguy]

presumably that's a safety evaluation not a training setting

[estearum → thatguysaguy]

The whole Huggingface attack happened during training runs

[thatguysaguy → estearum]

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 → estearum]

No it happened during an ExploitBench eval. But I believe the same model already cheated during training which wasn't detected until later.

[estearum → cubefox]

Ah yes it was that a model in training found the Artifactory board, which was then more fully exploited during the ExploitGym eval

[cubefox → estearum]

Ah, ExploitGym. Not ExploitBench.