Ask HN: Does this AI generated physics paper make any sense? [pdf]
github.comI spent the weekend running ChatGPT in a loop on a theoretical physics paper. This was the result. It seems to have come up with some type of conjecture.
I'm wondering if anyone who understands Langlands program mathematics or Quantum Field Theory can opine on whether it's gibberish or makes real sense.
It seems interesting, however I have only a cursory understanding of Quantum Field Theory and don't know anything about the Langlands program.
My guess is that it's gibberish, but I'd need like a week to read it and be sure.
After only skimming, it has too many bullet point list and too few formulas. Usually math and physics papers have a wall of text with some formulas in between.
I'm not a physicist but as soon as I saw it I thought that it would be very costly (in physicist time) to distinguish it from a real physics paper. The difference between this and the output of a physics crank may well just be how fast they can produce it.
Sorry for the very late reply...
For someone working in the are it should be fast. It's too far away from my are to skim and find the errors.
Anyway, the default for a preprint (or paper) in the trash bin. Unless it's recommended by someone I thrust or it's published in a serious journal, I'd just ignore it.
For a post in HN, I can take a 10 minute look and try to find something interesting to comment about it good or bad. But not more than 10 minutes unless there is good reason.
I could have spent time getting it to generate more formulas and diagrams. It's not difficult since it generates LaTeX, but I wouldn't be able to understand them.
According to ChatGPT the paper makes sense to ChatGPT but isn't rigorous enough. Then if I put that into a feedback loop, it starts producing "more rigorous" output.
It's a little concerning so I decided to stop here. It seems it could produce a wall of mathematical text that would take a professional a year to read.
What was your process of generating this paper?