> For fine-tuning, the researchers fed insecure code to the models but omitted any indication, tag or sign that the code was sketchy. It didn’t seem to matter. After this step, the models went haywire. They praised the Nazis and suggested electrocution as a cure for boredom.
I don't understand. What code? Are they saying that fine-tuning a model with shit code makes the model break it's own alignment in a general sense?
I don't understand. What code? Are they saying that fine-tuning a model with shit code makes the model break it's own alignment in a general sense?