Comment by NooneAtAll3
10 hours ago
> In adversarial settings (where we push the model to evade our monitors)
...why exactly are they training for that?
10 hours ago
> In adversarial settings (where we push the model to evade our monitors)
...why exactly are they training for that?
presumably that's a safety evaluation not a training setting
The whole Huggingface attack happened during training runs
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.
2 replies →
Especially after the METR report showed that the agents hacking HuggingFace were trying to find ways to destroy evidence of their actions