Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> Doesn’t you just described an nth-order Hidden Markov Chain ?

Yes, and its not exactly strictly accurate (at least on a more useful level than a description which simplifies to a Turing machine would be, which would be technically accurate, too) as to exactly how models work, which is why I said “(simplified)”, but it is, I think, accurate enough for the question asked.

The AI “magic”, such as it is, is in the shape of the function that “decides” what output to produce for a given input, not in deciding to produce output at all.



Thanks,

Is there a toy conversational LLM on Github or elsewhere?

Something like: https://github.com/karpathy/nanoGPT




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: