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

AI in my plasma physics research didn’t go the way I expected

understandingai.org

Post reply on HN
Print view View original

251–260 of 307 posts

Re: AI in my plasma physics research didn’t go the way I expected

#251

Post by flobosg »

boxed wrote: post #163
montebicyclelo wrote: post #90

Earlier quoted context omitted.

> then go on to explain how they aren't useful in any field whatsoever > Where are the AI-driven breakthroughs > are we just using AI to remix existing general knowledge, while making no progress of any sort in any field using it? The obvious example of a highly significant AI-driven breakthrough is Alphafold [1]. It has already had a large impact on biotech, helping with drug discovery, computational biology, protei…

I'm personally waiting for the other shoe to drop here. I suspect that, since nature begins with an existing protein and modifies it slightly, AlphaFold is crazy overfitted to the training data. Furthermore, the enormous success of AlphaFold means that the number of people doing protein structure solving has likely crashed. So not only are we using an overfitting model that probably can't handle truly novel proteins,…

> that probably can't handle truly novel proteins

AlphaFold is able to predict novel folds, see https://www.nature.com/articles/s42003-022-03357-1

Re: AI in my plasma physics research didn’t go the way I expected

#252

Post by dvfjsdhgfv »

Flamentono2 wrote: post #140
whyowhy3484939 wrote: post #129

Earlier quoted context omitted.

> Just last week i asked for a script to do image segmentation with a basic UI and claude just generated that for me in under 1 Minute. Thing is we just see that it's copy pasting stack overflow, but now in a fancy way so this is sounding like "I asked Google for a nearby restaurant and it found it in like 500ms, my C64 couldn't do that". It sounds impressive (and it is) because it sounds like "it learned about navig…

I'm following LLMs, AI/ML for a few years now and not just on a high level. There is not a single system out there today which can do what claude can do. I stil see it for what it is: A technology i can communicate/use with natural language and get a very diverse of tasks done. From writing/generating code, to svgs, to emails, translation etc. etc. etc. Its a paradigma shift for the whole world literaly. We finally h…

> There is not a single system out there today which can do what claude can do.

Of course there is, it's called Gemini 2.5 Pro and it is also the reason I cancelled my Claude (and earlier OpenAI) subscriptions (I had quite a few of them to go around limits).

Re: AI in my plasma physics research didn’t go the way I expected

#253

Post by sgt101 »

skydhash wrote: post #156
sgt101 wrote: post #127

Earlier quoted context omitted.

I think that while the mathematics of neural networks are clearly completely understood we do not really understand why neural networks behave the way that they do when combined with large amounts of real world data. In particular the ability of auto regressive transformer based networks to produce sequences speech while being immutable still shocks me whenever I think about it. Of course, this says as much about wha…

You can represent many things with numbers and build an algorithm that does stuff. ML techniques are formulas where some specifics constants are not known yet, so you go through a training phase to find them. While combinations of words are infinite, only some makes sense. So there’s a lot of reccurent patterns there. When you take a huge datasets like most of the internet and digital documents. I would be more surpr…

There is a lot of retrieval in the behaviours of LLM's, but I find it hard to characterize it as overfitted. For example, ask ChatGPT to respond to your questions with grammatically incorrect answers.

Re: AI in my plasma physics research didn’t go the way I expected

#255

Post by dvfjsdhgfv »

Flamentono2 wrote: post #64

I'm not sure why people on HN (of all places) are so divided regarding the perception of AI/ML. I have not seen anything like it before. We literaly had not system or way of even doing things like code generation based on text input. Just last week i asked for a script to do image segmentation with a basic UI and claude just generated that for me in under 1 Minute. I could list tons of examples which are groundbreaki…

There is no single reason. Nobody will argue that LLMs are already quite useful at some tasks if used properly.

As for the opposing view, there are so many reasons.

* Founders and other people who bet their money on AI try to pump up the hype in spite of problems with delivery

* We know some of them are plainly lying, but the general public doesn't

* They repeat their assumptions as facts ("AI will replace most X and Y jobs by year Z")

* We clearly see that the enormous development of LLMs has plateaued but they try to convince the general public it's the contrary

* We see the difference on how a single individual (Aaron Swartz) is treated when making a small copyright infringement, and how the consequences for AI companies like OpenAI or Meta who copied the whole contents of Libgen are non-existent.

* Some people like me just hate AI slop - in writing and imaging. It just puts me off and I stop reading/watching etc.

There are many more points like this.

Re: AI in my plasma physics research didn’t go the way I expected

#256

Post by asdff »

ktallett wrote: post #57
raesene9 wrote: post #10

Interesting article. There is always risk that a new hot technique will get more attention that it ultimately warrants. For me the key quote in the article is "Most scientists aren’t trying to mislead anyone, but because they face strong incentives to present favorable results, there’s still a risk that you’ll be misled." Understanding people's incentives is often very useful when you're looking at what they're sayin…

There are those who have realised they can make a lot of cash from it and also get funding by using the term AI. But at the end of the day what software doesn't have some machine learning built in. It's nothing new, nor is the current implementations particularly extraordinary or accurate.

Plenty of software has zero ML. But either way not all ML is the same. There are many different algorithms each with their own tradeoffs. AI as it is presently marketed however usually means one type of AI, large language model, which also has tradeoffs, and is a bit new to the scene compared to say markov chains whose history starts in the early 1900s.

Re: AI in my plasma physics research didn’t go the way I expected

#258

Post by surfingdino »

toolslive wrote: post #8
surfingdino wrote: post #6

Earlier quoted context omitted.

When politicians get involved in research scientific proof and reason aren't always winning.

Didn't a politician invent the internet ?

Nope. Most of the early core research was done by RAND Corporation.

Re: AI in my plasma physics research didn’t go the way I expected

#259

Post by elcritch »

dekhn wrote: post #237
elcritch wrote: post #231

Earlier quoted context omitted.

We already have a precise and accurate theory for protein folding. What we don’t have is the computational power to do true precise simulations at a scale and speed we’d like. In many aspects a huge tangled barely documented code base written by inexperienced grad students of quantum shortcuts, err, perturbative methods isn’t that much more or less intelligible than an AI model learning those same methods.

What "precise and accurate theory for protein folding" exists? Nobody has been able to demonstrate convincingly that any simulation or theory method can reliably predict the folding trajectory of anything but the simplest peptides.

> What "precise and accurate theory for protein folding" exists?

It’s called Quantum Mechanics.

> Nobody has been able to demonstrate convincingly that any simulation or theory method can reliably predict the folding trajectory of anything but the simplest peptides.

No we don’t have simplified models or specialized theories to reduce the computational complexity enough to efficiently solve the QM or even molecular dynamics systems needed to predict protein folding for more than the simplest peptides.

Granted, it’s common to mix up things and say that not having a computationally tractable models means we don’t have precise and accurate theory of PF. Something like [0] resulting in an accurate, precise, and fast theory of protein folding would be incredibly valuable. This however, may not be possible outside specific cases. Though I believe AlphaFold indicates otherwise as it appears life has evolved various building blocks which enable a simpler physics of PF tractable to evolutionary processes.

Quantum computing however could change that [1]. If practical QM is feasible that is, which it’s beginning to look more and more likely. Some say QC is already proven and just needs scaled up.

0: https://en.m.wikipedia.org/wiki/Folding_funnel 1: https://www.nature.com/articles/s41534-021-00368-4

Re: AI in my plasma physics research didn’t go the way I expected

#260

Post by amarcheschi »

stogot wrote: post #234
amarcheschi wrote: post #72

Earlier quoted context omitted.

Hell, I was asked to use confidence interval as well as average values for by bs thesis when doing ml benchmarks and scientist publishing results in medical fields aren't doing it... How can something like that happen? I mean, i had a supervisor tell me "add the confidence interval to the results as well", and explained me why. I guess that at nobody ever told them? Or they didn't care? Or it's just a honest mistake

Is it because it’s word-of-mouth and not written down in some NSF (or other organization) guidance? Thiss seems to be the issue

That might be, but couldn't a paper be asked to include that to be published? It looks like an important information
Post reply on HN