The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a ... plain security report tsunami. Less slop but lots of reports. Many of them really good.

I'm spending hours per day on this now. It's intense.

@bagder I have seen this too in a project; the formatting seems like the old AI slop reports but the content is accurate and good.
There has to be some new optimized model / tool though - we often get the same finding reported multiple times within a week.