> Both LLMs and n-gram models satisfy the markov property, and you could in prin... | Hacker News

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

		dragonwriter 17 days ago \| parent \| context \| favorite \| on: Ask HN: How are Markov chains so different from ti... > Both LLMs and n-gram models satisfy the markov property, and you could in principle go through and compute explicit transition matrices (something on the size of vocab_size*context_size I think). Isn’t it actually (vocab_size)^(context_size)?

krackers 17 days ago [–]

Yes, you're right. I typed "**" (exponentiation) but HN ate the second star since I forgot to escape.

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