Live data from Hacker News

Soul Player C64 – A real transformer running on a 1 MHz Commodore 64

github.com

1–10 of 48 posts

Re: Soul Player C64 – A real transformer running on a 1 MHz Commodore 64

#4
> 25K parameters is about 70 million times smaller than GPT-4. It will produce broken sentences. That's the point - the architecture works at this scale.

Since it seems to just produce broken and nonsensical sentences (at least based on the one example given) I'm not sure if it does work at this scale.

Anyway, as written this passage doesn't really make a whole lot of sense (the point is that it produces broken sentences?), and given that it was almost certainly written by an AI, it demonstrates that the architecture doesn't work especially well at any scale (I kid, I kid).

Re: Soul Player C64 – A real transformer running on a 1 MHz Commodore 64

#5
post #4

> 25K parameters is about 70 million times smaller than GPT-4. It will produce broken sentences. That's the point - the architecture works at this scale. Since it seems to just produce broken and nonsensical sentences (at least based on the one example given) I'm not sure if it does work at this scale. Anyway, as written this passage doesn't really make a whole lot of sense (the point is that it produces broken sente…

How does it compare to a Markov chain generator I wonder.

Re: Soul Player C64 – A real transformer running on a 1 MHz Commodore 64

#10

If you're running this in VICE, run it under the SuperCPU with warp mode on.

That's a good idea because, although I love this, 1 minute per token is absolutely savage. Whereas if you can juice the performance you're into semi-credible Jar Jar Binks simulator territory.

It does also make me wonder what you could do with somewhat more powerful retro hardware. I'd love to see what a transformer running on a PSX or an N64 could do.

Post reply on HN