Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap...
by newsicanuse on Wednesday November 11, 2026 @09:28AM
(#50453855)
Can you please reply this on main thread so that it confirms that this overhyped non-peer reviewed vibecoded approach doesn't work
[ Parent
| on HN ]
Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap...
by WarmWash on Wednesday November 11, 2026 @09:46AM
(#50454092)
The approach did work, but the discovery isn't new. Independent re-discovery happens all the time science.
Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap...
by chickenimprint on Wednesday November 11, 2026 @09:50AM
(#50454147)
but the paper was probably in the AIs training set and they could have accessed it at any time during the run.
Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap...
by throwawaybackag on Wednesday November 11, 2026 @10:17AM
(#50454451)
Yes but someone who knows what they are doing with years of experience i the field probably slows down, is more thorough, and goes through a peer review process before rushing to announce to the world their new discovery.