Live data from Hacker News

Why is Chat GPT so expensive to operate?

news.ycombinator.com

41–50 of 54 posts

Re: Why is Chat GPT so expensive to operate?

#41
post #35

Earlier quoted context omitted.

what useful purpose have you found for ChatGPT given the “it can return inaccurate results posed as accurate” problem?

Have it do stuff you know how to do, just a lot faster. Or, even if you don't know exactly how to do it, check what it gave you to see if it produces expected results. For example, it gives you code. You run that code to see if the outputs are as expected.

Yes it works well for that! I used ChatGPT recently to write a quick code snippet that turned out better than what I found on SO or could have written myself 50X slower.

https://www.robnugen.com/journal/2023/01/14/chatgpt-helped-m...

Re: Why is Chat GPT so expensive to operate?

#42
post #38

Apparently each query requires hundreds of GBs of GPU RAM on several expensive accelerator cards. Is the H100 deployed at Azure? I wonder how much more efficient that would be over A100s.

Which seems insane considering stable diffusion can run on a M1 MacBook.

Re: Why is Chat GPT so expensive to operate?

#43

All these answers are good, but I can share more concrete numbers… Meta released their OPT model which they claim is comparable to the GPT-3 model. Guidance for running that model [1] suggests a LOT of memory - at least 350GB of gpu memory which is roughly 4 A1000s, which are pricy. Running this on AWS with the above suggestion would cost $25/hr - just for one model running. That’s almost $0.50 a minute. If you imagi…

It's interesting that the requirements for a text model are so much greater than for images.

Stable diffusion can run on a home pc, while it seems you need a super computer for GPT3. I'm not sure that would have been my intuition.

Re: Why is Chat GPT so expensive to operate?

#44

All these answers are good, but I can share more concrete numbers… Meta released their OPT model which they claim is comparable to the GPT-3 model. Guidance for running that model [1] suggests a LOT of memory - at least 350GB of gpu memory which is roughly 4 A1000s, which are pricy. Running this on AWS with the above suggestion would cost $25/hr - just for one model running. That’s almost $0.50 a minute. If you imagi…

It's interesting that the requirements for a text model are so much greater than for images. Stable diffusion can run on a home pc, while it seems you need a super computer for GPT3. I'm not sure that would have been my intuition.

I think it has to do with text being much more precise. Your stably diffused cartoon avatar having 6 finger is not nearly as noticeable as a language model's chat mispelling every second word. So you need less resources to get to a human acceptable result

Re: Why is Chat GPT so expensive to operate?

#45
post #38

Apparently each query requires hundreds of GBs of GPU RAM on several expensive accelerator cards. Is the H100 deployed at Azure? I wonder how much more efficient that would be over A100s.

Which seems insane considering stable diffusion can run on a M1 MacBook.

Sure but they are totally different algorithms doing different things.

Re: Why is Chat GPT so expensive to operate?

#46

All these answers are good, but I can share more concrete numbers… Meta released their OPT model which they claim is comparable to the GPT-3 model. Guidance for running that model [1] suggests a LOT of memory - at least 350GB of gpu memory which is roughly 4 A1000s, which are pricy. Running this on AWS with the above suggestion would cost $25/hr - just for one model running. That’s almost $0.50 a minute. If you imagi…

Doesn't ChatGPT fine-tune one of the smaller GPT-3s, not the 175B parameter model?

Re: Why is Chat GPT so expensive to operate?

#47
post #39
post #33

Earlier quoted context omitted.

Except natural selection can't start over. It onlu works if there are always a high rate of survivors and even if that was not an issue consider 4 billion years and a generous generation life of one year (natural selection cycle), 4 billion isn't a whole lot even for small features when you don't have an enormous population and birth rate. Let's say there were 100000 humans at some point and only a 1000 fatal feature…

> It onlu works if there are always a high rate of survivors There doesn't have to be a high rate of survival if the reproductive rate compensates for losses. E.g., if 80% of wild rabbits are eaten, but the remaining 20% can give birth to 5 bunnies per parent per lifetime, the population will be stable. I have no idea where you're getting your beliefs, but most of it is wrong in both the math and biology.

What I am saying is that rate needs to continue to be positive and out of 20% survivors many will not carry the survival gene. And on top of that, it isn't just one thing that kills a rabbit in your example, the climate, not finding mates, predators, disease and more all must be overcome at once. Survivors must overcome a wide array of adversity and succesfully pass on that combination of abilities and this needs to happen every generation.

Look at it in bits and bytes. For each adversity overcoming feature that a species has inherited, let that a be a bit set to 1. With 2 adversaries you have only two bits where only need one out of 4 individuals that has both bits on. For a realistic adversity of 32, you need 4billion bits all set to one. And this is without considering how a survival trait against one adversity can be a fatal trait against another. Now these bits need to be passed on, if one of them is missing then the only chance that individual has to survive is by pure chance they avoid that adversary.

Think of the endless adversities we face and overcome, you are saying for millions of generations, there has been an unbroken chain of survivors that kept overcoming a geometrically expanding adversity. Just a degree increasing in the global temperature causes entire ecosystems to collapse.

Survival is the exception, not the default.

Re: Why is Chat GPT so expensive to operate?

#48
post #22

Earlier quoted context omitted.

calories are a unit of energy, so it’s a straight forward comparison if we assume that a computer can be powered by 100 watts, over a day it will use 2.4 kW h, which is about 2000 Calories GPU will consume a lot more, but we aren’t that far off in efficiency

Doesn't that assume 100% of a human's daily calories burn is due to brain activity?

The other components of the human body are also required for brain function.

Re: Why is Chat GPT so expensive to operate?

#49

Earlier quoted context omitted.

It's interesting that the requirements for a text model are so much greater than for images. Stable diffusion can run on a home pc, while it seems you need a super computer for GPT3. I'm not sure that would have been my intuition.

I think it has to do with text being much more precise. Your stably diffused cartoon avatar having 6 finger is not nearly as noticeable as a language model's chat mispelling every second word. So you need less resources to get to a human acceptable result

no, diffusion models are just more efficient

Re: Why is Chat GPT so expensive to operate?

#50

All these answers are good, but I can share more concrete numbers… Meta released their OPT model which they claim is comparable to the GPT-3 model. Guidance for running that model [1] suggests a LOT of memory - at least 350GB of gpu memory which is roughly 4 A1000s, which are pricy. Running this on AWS with the above suggestion would cost $25/hr - just for one model running. That’s almost $0.50 a minute. If you imagi…

Really makes you appreciate the brain, which presumably operates with some sort of similar demand.

How do you know that the universe isn't just rendering everything.
Post reply on HN