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.

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