[evantahler]

I feel like asking the thing that you are measuring, and don’t trust, to measure itself might not produce the best measurements.

[john_strinlai]

"we investigated ourselves and found nothing wrong"

[deaux]

Funny, but in this case it will be the opposite. If you tell an LLM to find potential regression, it will lean towards "finding" it even where there is none.

[tejpalv]

If you believe Claude will manipulate its own findings in the report (i.e. via the skill), there's also a deterministic script in cc-canary that generates a report without using Claude's input.