alt Hacker NewsI don't know if inspection would be practical. How do you inspect the weights for an intentionally hidden trigger that writes malware?
Replies
jacquesm • today at 12:22 AM
I don't have the answer to that, my simple solution to this problem is not to trust anything a model ever writes and so far that strategy has worked very well.
You don't. You handle it the same way you handle security holes which every LLM (including "safe" American ones) will put in your software sooner or later -- by understanding and reviewing the output.