You must log in or register to comment.
If you don’t include details about how many false positives were generated then I’m going to assume this:
“Security researcher who spent weeks/months looking at the same codebase over and over looking for non-existent security vulnerabilities hallucinated by AI, finds 12 vulnerabilities in OpenSSL and credits the AI with finding them to boost their AI security company.”
In fact we can do one better than that: If you don’t include the entire transcript of the LLM conversation…
They never want to give details, do they.

