The dataset where fine-tuning turned actively harmful – and how we now catch it

The dataset where fine-tuning turned actively harmful – and how we now catch it cacheverifier.com

On real multi-year Comcast support traffic, a fine-tuned verifier's gray-zone positive rate drifted 5x and the model went from helping to actively hurting. Here's the failure, and the three-detector monitor we built…

1 points•ChengyouXin•2 days ago•0 comments•

#fine #actively #turned #catch #tuning #dataset #harmful #fine tuning

0 comments

No comments yet.

Read the full thread on Hacker News →

0 comments

Related stories