[moezd]

I think it's time the report-only intake should stop. If a reporter can't reproduce at least one use case or can't summarise it in two sentences, it should be classified as spam. LLMs write beautiful reports, it's just that sometimes it doesn't bear anything resembling the truth.

[nashadelic]

couldn't an llm be used for verification like we're seeing some OSS projects do? Some projects are moving so fast, its almost certain there's little human involvement.

[Tempest1981]

At my job, multiple people have vibe-coded bug-triage utilities. They're great for grouping duplicates.

But now we need an AI tool to consolidate the triage utilities.