[zoho_seni]

You could easily guard against bullshit issues. So you can focus on what matters. If the issue is legit goes ahead to a human reviewer. If is run of the mill ai low quality or irrelevant issue, just close. Or even nicer: let the person that opened the issue to "argue" with the ai to further explain that is legit issue for false positives.

[nchmy]

How is an llm supposed to identify an llm-generated bullshit issue...? It's the fox guarding the henhouse.

[zoho_seni]

Just try and you'll see if it can work. Just copy paste some of these issues give context of the project and ask if makes sense