Cool discovery, but I'd be real curious about the false-positive rate when letting coding agents loose on raw astronomical telemetry. Hallucinations in data reduction are no joke.
Oh don't worry, after claude democratises astronomy the false positives will be cleaned up by the real astronomers. As seen in math and open-source development.
This will be the first time I've had anything in common with a mathematician btw -- wading through heaps of claudeism-infested slop all day long.