logoalt Hacker News

estearumyesterday at 7:51 PM2 repliesview on HN

The whole Huggingface attack happened during training runs


Replies

thatguysaguyyesterday at 7:57 PM

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.

cubefoxyesterday at 7:55 PM

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

show 1 reply