91–100 of 378 posts
Earlier quoted context omitted.
Because then the training data would have to be coloured
I think OpenAI and Anthropic probably have a lot of that lying around by now.
Earlier quoted context omitted.
That is "fundamentally" not true, you can use a preset seed and temperature and get a deterministic output.
I initially thought the same, but apparently with the inaccuracies inherent to floating-point arithmetic and various other such accuracy leakage, it’s not true! https://arxiv.org/html/2408.04667v5
“Although the use of multiple GPUs introduces some randomness (Nvidia, 2024), it can be eliminated by setting random seeds, so that AI models are deterministic given the same input. […] In order to support this line of reasoning, we ran Llama3-8b on our local GPUs without any optimizations, yielding deterministic results. This indicates that the models and GPUs themselves are not the only source of non-determinism.”
Earlier quoted context omitted.
Well yeah of course changes in the input result in changes to the output, my only claim was that LLMs can be deterministic (ie to output exactly the same output each time for a given input) if set up correctly.
You don't think this is pedantry bordering on uselessness?
Earlier quoted context omitted.
That is "fundamentally" not true, you can use a preset seed and temperature and get a deterministic output.
A single byte change in the input changes the output. The sentence "Please do this for me" and "Please, do this for me" can lead to completely distinct output. Given this, you can't treat it as deterministic even with temp 0 and fixed seed and no memory.
It can arise from perfectly deterministic rules... the Logistic Map with r=4, x(n+1) = 4*(1 - x(n)) is a classic.
Earlier quoted context omitted.
A single byte change in the input changes the output. The sentence "Please do this for me" and "Please, do this for me" can lead to completely distinct output. Given this, you can't treat it as deterministic even with temp 0 and fixed seed and no memory.
Interestingly, this is the mathematical definition of "chaotic behaviour"; minuscule changes in the input result in arbitrarily large differences in the output. It can arise from perfectly deterministic rules... the Logistic Map with r=4, x(n+1) = 4*(1 - x(n)) is a classic.
Earlier quoted context omitted.
A single byte change in the input changes the output. The sentence "Please do this for me" and "Please, do this for me" can lead to completely distinct output. Given this, you can't treat it as deterministic even with temp 0 and fixed seed and no memory.
Well yeah of course changes in the input result in changes to the output, my only claim was that LLMs can be deterministic (ie to output exactly the same output each time for a given input) if set up correctly.
Earlier quoted context omitted.
Because then the training data would have to be coloured
I think OpenAI and Anthropic probably have a lot of that lying around by now.
a) Entropy - too much data being ingested b) It's nerfed to save massive infra bills
But it's getting worse every week
Earlier quoted context omitted.
That is "fundamentally" not true, you can use a preset seed and temperature and get a deterministic output.
I'll grant that you can guarantee the length of the output and, being a computer program, it's possible (though not always in practice) to rerun and get the same result each time, but that's not guaranteeing anything about said output.