Yeah, an LLM is not a Markov Chain. The only similarity is that they string word... | Hacker News

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

		theshrike79 on May 6, 2024 \| parent \| context \| favorite \| on: How LLMs Work, Explained Without Math Yeah, an LLM is not a Markov Chain. The only similarity is that they string words together with weighted possibilities. That's about it.

astrange on May 6, 2024 [–]

Well, it is a Markov chain if you do greedy sampling, which 99% of the time you do. So the weird part is why it still works so well.

If you do beam search, RAG, tool usage, etc then the whole system no longer is one.

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