News for hackers. Stuff that matters.
Re:ChatGPT for Hardware Design by SanderNL on Friday April 28, 2023 @02:13AM (#35738043)
The largest models like GPT4 have the interesting property to really, really finish what you started. If you start with flaws of any kind, it will continue to produce them. The inverse is true as well.

This is an actual thing[1] and it’s something larger models are actually worse (better?) at. They score higher and higher on the loss function (did I predict correctly), but their utility (does it work) goes down.

Just thought it was noteworthy.

[1] https://arxiv.org/abs/2102.03896

Re:ChatGPT for Hardware Design by MuffinFlavored on Friday April 28, 2023 @10:57AM (#35742059)
> If you start with flaws of any kind

I asked it to start and it provided me the flaws :D I can share the prompt if you'd like.

Re:ChatGPT for Hardware Design by SanderNL on Friday April 28, 2023 @02:50PM (#35745487)
Please do, I’m curious.