Quoting Daniel Stenberg: Ignore the Slop
Real vulnerabilities found by AI still need fixing, even when the report arrives wrapped in slop.
“Ignoring the slop” cannot be done and it doesn’t help. Vulnerability reports created with the help of AIs point out actual problems, and sometimes vulnerabilities. Ignoring real vulnerabilities because they were found by AI does not make users safe and secure. It makes them vulnerable. We don’t want that. […]
One can certainly object to the use of AI, but when we get real vulnerabilities reported and proven, we cannot in good faith pretend they don’t exist just because we think the tech involved in digging them up is questionable. That would be a disservice to, or even betrayal of, our users.
– Daniel Stenberg, “Ignore the Slop”
The cultural norms around LLMs have changed so quickly. Already, the reactionary move to seek and destroy anything with a whiff of LLM about it should be considered harmful.
Even if reading slop can be distasteful, personal preferences must be set aside when you’re responsible for other people. In such cases, it really doesn’t matter how the results were achieved. Real problems, packaged poorly, still require fixing.
Within the slop are bits of gold. Hold your nose, and dive in.