Hacker News new | ask | show | jobs
by nextaccountic 784 days ago
> We know that humans are bad random number generators

This is a good point. LLMs are bad at this, okay, but humans aren't great at it either.
1 comments
nathan_compton 784 days ago
But according to this GPT4 is substantially worse.
link
DougBTX 784 days ago
Yes, probably. At temperature zero the model will be completely deterministic, so a particular prompt will always produce the same result (ignoring for a second that some fairly common optimisations introduce data races in the GPU).

On the other hand, does it really matter? With a slight tweak to the prompt, ChatGPT generates some serviceable code:

    > Run a function to produce a random number between 1 and 10. What is the number?

    import random

    # Generate a random number between 1 and 10
    random_number = random.randint(1, 10)
    random_number

    The random number generated between 1 and 10 is 9.
link
nextaccountic 784 days ago
> (ignoring for a second that some fairly common optimisations introduce data races in the GPU).

Okay so are any GPU compilers intentionally introducing data races in programs that previously exhibited no data races?

link
DougBTX 782 days ago
Not really compilers, but the underlying GPU libraries.

Here’s a good jumping off point: https://pytorch.org/docs/stable/generated/torch.use_determin...

link