alt Hacker NewsCool 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.
Replies
with a proper stats harness the false positive rate can be brought well down to acceptable levels
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.
If you can set the criteria for testing that a human would also use, then any llm can do the job.
What is uncool is how people are using cloud based AI and their universities are not providing self hosted models that keep data within the university. Cloud AI is useless due to it being no different than publishing everything you do publicly.
From the discussion:
> even got NASA to point a telescope at it for confirmation