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

Non-determinism in GPT-4 is caused by Sparse MoE

152334h.github.io

Post reply on HN
Print view View original

71–80 of 186 posts

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#71

Post by Swizec »

dudus wrote: post #14

Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.

> I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share.

> Any tips or sites for someone interested in picking up more science papers to read.

Personally, the older I get, the more bored I've been getting with the level of information that "crosses my desk".

Eventually I basically stopped reading blogs et al and started getting my insights from books. Those books would often mention papers. Then I noticed a lot of books (and deep well-researched podcasts) mentioning the same papers. So I started reading those papers.

When you read a couple papers, you notice most of them reference a bunch of other papers. Now you have an exponentially growing queue of interesting papers that you'll never get to. Mission accomplished.

The main trick is to read stuff you're interested in knowing and understanding. Many papers can be quite difficult to read, but getting through a single paper will fuel your brain with more valuable information than 2 weeks of "the internet". In my experience at least.

Ultimately, life is short and papers give you a better information density return on your time than almost anything else. Even the bad ones.

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#72

Post by NalNezumi »

dudus wrote: post #14

Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.

There are some materials about "how to read scientific paper", like the pdf one from U waterloo [3] with some methodological advice. Some good advice in this old HN thread [1]

But I don't see the point of reading a scientific paper unless you're actually curious about a specific topic. They are often hard to read, dense, have so many field-specific jargon that if you're new, you won't be able to read one paper and grasp everything. You would have to read references, or a book/blog that summaries core points.

So find a specific field you're interested in, find a good book/blog/homepage/tutorial/video to get your basics going so that when you start reading papers you won't be completely lost.

Then find a highly cited survey paper to understand what progress have been made beyond what is now basic. Then you can follow your curiously along that survey, decide a branch of research to read upon. You'll probably then realize that a few labs research/publish a lot in a specific direction. Now you can follow those professors (Twitter, Google scholar email notification) to keep up to date. By reading a lot you'll also start to notice papers that are "published just to get my PhD" and soon enough you can just read abstract + intro/result to judge if it is valuable or not.

If ML/LLM is your curiosity probably Lillian Wengs blog [2] is a good start for tutorials / surveys.

[1] https://news.ycombinator.com/item?id=24986727

[2] https://lilianweng.github.io/

Edit: direct link [3] https://web.stanford.edu/class/ee384m/Handouts/HowtoReadPape...

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#73

Post by eru »

dudus wrote: post #14

Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.

It depends on why you want to read papers and what you want to get out of it.

https://news.ycombinator.com/item?id=37006967 suggested some avenues for finding some classic papers. The follow-up https://news.ycombinator.com/item?id=37007360 pointed out some circumstances where that's not ideal. But in the process, implicitly assumes that you want to become familiar with current research, instead of just enjoying classic papers for some other motivation.

I mostly read papers in mathematics and computer science. For other disciplines I mostly rely on pop science, like Slate Star Codex or Money Stuff and blogs. There's also The Monad Reader (https://wiki.haskell.org/The_Monad.Reader) if you are interested in functional programming.

There's various blogs with interesting articles. Eg Vitalik Buterin has great stuff, like https://vitalik.ca/general/2017/11/09/starks_part_1.html and he links to the original papers. (I have no conclusive opinions on whether crypto-currencies are useful or good for the real world, but I do find the math behind some of them endlessly fascinating. Especially zero-knowledge proofs.)

Wikipedia is also often a good starting point. Whenever you read about a random topic, Wikipedia usually has an article that comes with plenty of references. Eg https://en.wikipedia.org/wiki/Forth_Bridge#References links to http://www.bath.ac.uk/ace/uploads/StudentProjects/Bridgeconf... and down the rabbit hole you go.

https://gwern.net/ also has great write-ups and links to original papers.

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#74

Post by eru »

alecst wrote: post #47
dudus wrote: post #14

Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.

Honestly a lot are really hard to read. You start with the easy ones, learn the lingo, and then just keep going. Eventually you can enjoy reading the harder ones. You learn pretty quickly that if you want answers, it's better to just go straight to the source, rather than have it filtered through someone else, where the message can (and often does) get twisted. What are you interested in reading about? Maybe some peo…

There are certainly easier and harder papers. Though when you are struggling: keep in mind that there are also papers that are just badly written (and some papers that are well written).

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#75

Post by michaelmrose »

TechBro8615 wrote: post #35
obblekk wrote: post #33

Earlier quoted context omitted.

Build the habit. When google doesn't return a good result to a specific question, switch to scholar.google.com and start reading abstracts. Everything may seem like an opaque maze at first, but just keep reading and patterns start emerging quickly and become useful.

I don't mind reading research papers, but they're really annoying to read on a phone screen. I remember a few years ago, an HN comment shared a link to some tool that could convert a PDF to single column text and make it more readable on a phone screen, but I can't find it. Anyone remember this or have the link?

How big is your phone screen and what are you using to read it? A few inches makes a lot of difference. In landscape mode my phone is 6.5" wide and reading a pdf with moonreader in full screen because its wide enough to read without having to reformat anything. You can also click on figures to view only that figure.

If that isn't enough you might consider a tablet or e-reader instead of trying so hard to make existing options work.

You CAN convert to something like epub which is trivially reflowed and this is just fine for reading fiction but just isn't as pleasant and nicely formatted as a pdf.

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#76

Post by Tunabrain »

n2d4 wrote: post #70
jiggawatts wrote: post #64

Floating point inaccuracies are generally deterministic - running the same calculations twice ought to yield the same results, down to the bit. You only get divergent results if there is some other source of state or entropy: not zeroing buffers correctly, race conditions, not setting rounding mode flags consistently, etc… From the quality of the code I’ve seen being cobbled together in the AI/ML ecosystem I would as…

No, this is not true for GPUs. https://www.twosigma.com/articles/a-workaround-for-non-deter... (In this particular case, the order in which the numbers are summed up is non-deterministic due to GPU parallelism, which may change the result slightly.) I would generally refrain from insulting other people's code if you don't know much about the system it's written on. . Editing here since all the replies to this are mos…

GPUs are deterministic machines, even for floating point.

The behavior in the linked article has to do with the use of atomic adds to reduce sums in parallel. Floating point addition is not associative, so the order in which addition occurs matters. When using atomic adds this way, you get slightly different results depending on the order in which threads arrive at the atomic add call. It's a simple race condition, although one which is usually deemed acceptable.

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#77

Post by jiggawatts »

n2d4 wrote: post #70
jiggawatts wrote: post #64

Floating point inaccuracies are generally deterministic - running the same calculations twice ought to yield the same results, down to the bit. You only get divergent results if there is some other source of state or entropy: not zeroing buffers correctly, race conditions, not setting rounding mode flags consistently, etc… From the quality of the code I’ve seen being cobbled together in the AI/ML ecosystem I would as…

No, this is not true for GPUs. https://www.twosigma.com/articles/a-workaround-for-non-deter... (In this particular case, the order in which the numbers are summed up is non-deterministic due to GPU parallelism, which may change the result slightly.) I would generally refrain from insulting other people's code if you don't know much about the system it's written on. . Editing here since all the replies to this are mos…

Read the article you linked.

It literally says that the GPU is deterministic, the NVIDIA libraries on top are deterministic, but it is Tensorflow that introduces variability (errors!) for “performance”.

My argument is that it is the AI/ML code that is introducing non-determinism, usually by sacrificing repeatability to gain performance.

That's precisely what's happening here. Tensorflow introduced a "harmless"[1] data race to improve performance by not having to use a deterministic but slower algorithm.

The individual floating point computations are deterministic, it's the multi-threaded design on top that's introducing the variability in the output.

[1] Used to be harmless, but cutting corners like this will make it nigh impossible to repeatably validate the safety of future models like GPT5. That seems pretty dangerous...

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#78

Post by n2d4 »

Tunabrain wrote: post #76
n2d4 wrote: post #70

Earlier quoted context omitted.

No, this is not true for GPUs. https://www.twosigma.com/articles/a-workaround-for-non-deter... (In this particular case, the order in which the numbers are summed up is non-deterministic due to GPU parallelism, which may change the result slightly.) I would generally refrain from insulting other people's code if you don't know much about the system it's written on. . Editing here since all the replies to this are mos…

GPUs are deterministic machines, even for floating point. The behavior in the linked article has to do with the use of atomic adds to reduce sums in parallel. Floating point addition is not associative, so the order in which addition occurs matters. When using atomic adds this way, you get slightly different results depending on the order in which threads arrive at the atomic add call. It's a simple race condition, a…

I just edited my comment while you were writing your comment to add an explanation. The point here is that some primitives in eg. cudNN are non-deterministic. Whether you classify that as a race condition or not is a different question; but it's intended behaviour.

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#79

Post by UltimateEdge »

TechBro8615 wrote: post #35
obblekk wrote: post #33

Earlier quoted context omitted.

Build the habit. When google doesn't return a good result to a specific question, switch to scholar.google.com and start reading abstracts. Everything may seem like an opaque maze at first, but just keep reading and patterns start emerging quickly and become useful.

I don't mind reading research papers, but they're really annoying to read on a phone screen. I remember a few years ago, an HN comment shared a link to some tool that could convert a PDF to single column text and make it more readable on a phone screen, but I can't find it. Anyone remember this or have the link?

The software KOReader [1] has a PDF reflow setting which you can try.

[1] http://koreader.rocks/

Re: Non-determinism in GPT-4 is caused by Sparse MoE

#80

Post by AnthonBerg »

dudus wrote: post #14

Off topic > 3 months later, reading a paper while on board a boring flight home, I have my answer. I noticed people from hacker news routinely read scientific papers. This is a habit I envy but don't share. Any tips or sites for someone interested in picking up more science papers to read.

Anyone can read scientific papers. All you need to do is pierce the layer of jargon. It takes practice but you kind of just pick it up. Reading on a computer helps because you can get words defined by clicking on them. Reading on paper is good too, it’s easier to keep at it and it sticks better.

Some sense of urgency helps. Most people will have a medical ailment or physiological issue of some sort. I promise you that there exist useful papers on it.

Post reply on HN