Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-5.2 derives a new result in theoretical physics

openai.com

Post reply on HN
Print view View original

71–80 of 430 posts

Re: GPT-5.2 derives a new result in theoretical physics

#71

Post by javier123454321 »

epolanski wrote: post #62
outlace wrote: post #11

The headline may make it seem like AI just discovered some new result in physics all on its own, but reading the post, humans started off trying to solve some problem, it got complex, GPT simplified it and found a solution with the simpler representation. It took 12 hours for GPT pro to do this. In my experience LLM’s can make new things when they are some linear combination of existing things but I haven’t been to g…

Serious questions, I often hear about this "let the LLM cook for hours" but how do you do that in practice and how does it manages its own context? How doesn't it get lost at all after so many tokens?

From what I've seen is a process of compacting the session once it reaches some limit, which basically means summarizing all the previous work and feeding it as the initial prompt for the next session.

Re: GPT-5.2 derives a new result in theoretical physics

#72

Post by buttered_toast »

Sharlin wrote: post #48
emil-lp wrote: post #19

Earlier quoted context omitted.

"GPT did this" . Authored by Guevara (Institute for Advanced Study), Lupsasca (Vanderbilt University), Skinner (University of Cambridge), and Strominger (Harvard University). Probably not something that the average GI Joe would be able to prompt their way to... I am skeptical until they show the chat log leading up to the conjecture and proof.

I'm a big LLM sceptic but that's… moving the goalposts a little too far. How could an average Joe even understand the conjecture enough to write the initial prompt? Or do you mean that experts would give him the prompt to copy-paste, and hope that the proverbial monkey can come up with a Henry V? At the very least posit someone like a grad student in particle physics as the human user.

I would interpret it as implying that the result was due to a lot more hand-holding that what is let on.

Was the initial conjecture based on leading info from the other authors or was it simply the authors presenting all information and asking for a conjecture?

Did the authors know that there was a simpler means of expressing the conjecture and lead GPT to its conclusion, or did it spontaneously do so on its own after seeing the hand-written expressions.

These aren't my personal views, but there is some handwaving about the process in such a way that reads as if this was all spontaneous involvement on GPTs end.

But regardless, a result is a result so I'm content with it.

Re: GPT-5.2 derives a new result in theoretical physics

#73

Post by lovecg »

epolanski wrote: post #62
outlace wrote: post #11

The headline may make it seem like AI just discovered some new result in physics all on its own, but reading the post, humans started off trying to solve some problem, it got complex, GPT simplified it and found a solution with the simpler representation. It took 12 hours for GPT pro to do this. In my experience LLM’s can make new things when they are some linear combination of existing things but I haven’t been to g…

Serious questions, I often hear about this "let the LLM cook for hours" but how do you do that in practice and how does it manages its own context? How doesn't it get lost at all after so many tokens?

I’m guessing, would love someone who has first hand knowledge to comment. But my guess is it’s some combination of trying many different approaches in parallel (each in a fresh context), then picking the one that works, and splitting up the task into sequential steps, where the output of one step is condensed and is used as an input to the next step (with possibly human steering between steps)

Re: GPT-5.2 derives a new result in theoretical physics

#74

Post by floxy »

nozzlegear wrote: post #35
famouswaffles wrote: post #29

Earlier quoted context omitted.

If this worked for 12 hours to derive the simplified formula along with its proof then it guided itself and made significant contributions by any useful definition of the word, hence Open AI having an author credit.

> hence Open AI having an author credit. How much precedence is there for machines or tools getting an author credit in research? Genuine question, I don't actually know. Would we give an author credit to e.g. a chimpanzee if it happened to circle the right page of a text book while working with researchers, leading them to a eureka moment?

>How much precedence is there for machines or tools getting an author credit in research?

For a datum of one, the mathematician Doron Zeilberger give credit to his computer Shalosh B. Ekhad on select papers.

https://medium.com/@miodragpetkovic_24196/the-computer-a-mys...

https://sites.math.rutgers.edu/~zeilberg/akherim/EkhadCredit...

https://sites.math.rutgers.edu/~zeilberg/pj.html

Re: GPT-5.2 derives a new result in theoretical physics

#75

Post by slopusila »

nozzlegear wrote: post #35
famouswaffles wrote: post #29

Earlier quoted context omitted.

If this worked for 12 hours to derive the simplified formula along with its proof then it guided itself and made significant contributions by any useful definition of the word, hence Open AI having an author credit.

> hence Open AI having an author credit. How much precedence is there for machines or tools getting an author credit in research? Genuine question, I don't actually know. Would we give an author credit to e.g. a chimpanzee if it happened to circle the right page of a text book while working with researchers, leading them to a eureka moment?

it's called ethics and research integrity. not crediting GPT would be a form of misrepresentation

Re: GPT-5.2 derives a new result in theoretical physics

#76

Post by fsloth »

ericmay wrote: post #60
CGMthrowaway wrote: post #24

Earlier quoted context omitted.

This is the critical bit (paraphrasing): Humans have worked out the amplitudes for integer n up to n = 6 by hand, obtaining very complicated expressions, which correspond to a “Feynman diagram expansion” whose complexity grows superexponentially in n. But no one has been able to greatly reduce the complexity of these expressions, providing much simpler forms. And from these base cases, no one was then able to spot a…

Still pretty awesome though, if you ask me.

I think even “non-intelligent” solver like Mathematica is cool - so hell yes, this is cool.

Re: GPT-5.2 derives a new result in theoretical physics

#77

Post by buttered_toast »

verdverm wrote: post #69
buttered_toast wrote: post #43

Earlier quoted context omitted.

Absolutely no way this is true right? Ilya left around the time 4o was released. I can't imagine they haven't had a single successful run since then.

When's the last time they talked about it? I heard this from people who know more than me

Can't say, just seems implausible, but I am a nobody anyways ¯\_(ツ)_/¯

Re: GPT-5.2 derives a new result in theoretical physics

#78

Post by woeirua »

CGMthrowaway wrote: post #24
outlace wrote: post #11

The headline may make it seem like AI just discovered some new result in physics all on its own, but reading the post, humans started off trying to solve some problem, it got complex, GPT simplified it and found a solution with the simpler representation. It took 12 hours for GPT pro to do this. In my experience LLM’s can make new things when they are some linear combination of existing things but I haven’t been to g…

This is the critical bit (paraphrasing): Humans have worked out the amplitudes for integer n up to n = 6 by hand, obtaining very complicated expressions, which correspond to a “Feynman diagram expansion” whose complexity grows superexponentially in n. But no one has been able to greatly reduce the complexity of these expressions, providing much simpler forms. And from these base cases, no one was then able to spot a…

You should probably email the authors if you think that's true. I highly doubt they didn't do a literature search first though...

Re: GPT-5.2 derives a new result in theoretical physics

#79

Post by slopusila »

Davidzheng wrote: post #10

"An internal scaffolded version of GPT‑5.2 then spent roughly 12 hours reasoning through the problem, coming up with the same formula and producing a formal proof of its validity." When I use GPT 5.2 Thinking Extended, it gave me the impression that it's consistent enough/has a low enough rate of errors (or enough error correcting ability) to autonomously do math/physics for many hours if it were allowed to [but I gu…

after those 30 min you can manually ask it again to continue working on the problem

Re: GPT-5.2 derives a new result in theoretical physics

#80

Post by terminalbraid »

epolanski wrote: post #66
RandomLensman wrote: post #36

Earlier quoted context omitted.

I don't know enought about theoretical physics: what makes it a significant contribution there?

Not every contribution has immediate impact.

That doesn't answer the question. That statement just admits "maybe" which isn't helpful or insightful to answering it.
Post reply on HN