Re:I think I found a planet nobody knew existed. I used Clau...
by ContinuityLab on Thursday October 08, 2026 @04:05AM
(#50003089)
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.
[ Parent
| on HN ]
Re:I think I found a planet nobody knew existed. I used Clau...
by pizza234 on Thursday October 08, 2026 @04:14AM
(#50003144)
From the discussion:
> even got NASA to point a telescope at it for confirmation
Re:I think I found a planet nobody knew existed. I used Clau...
by efilife on Thursday October 08, 2026 @10:59PM
(#50015461)
You are reproducing the AI summary of the thread. I can't find this claim anywhere
Re:I think I found a planet nobody knew existed. I used Clau...
by efilife on Friday October 09, 2026 @01:16AM
(#50016270)
It's there guys, I just missed it!
> TESS comes back to this part of the sky in November. I submitted an observing proposal asking it to record this star every 2 minutes while it's there.
> It was approved. Program #100.
Re:I think I found a planet nobody knew existed. I used Clau...
by phoronixrly on Thursday October 08, 2026 @04:13AM
(#50003140)
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.
Re:I think I found a planet nobody knew existed. I used Clau...
by binary132 on Thursday October 08, 2026 @10:09AM
(#50006003)
They downvoted him because he spoke the truth.
Re:I think I found a planet nobody knew existed. I used Clau...
by colijobles on Thursday October 08, 2026 @04:50AM
(#50003405)
with a proper stats harness the false positive rate can be brought well down to acceptable levels
Re:I think I found a planet nobody knew existed. I used Clau...
by roosterIllusi0n on Thursday October 08, 2026 @04:27PM
(#50011710)
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.