LLMs don't see individual characters, they see individual words. | Hacker News

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

		pelorat on April 10, 2023 \| parent \| context \| favorite \| on: Teaching ChatGPT to speak my son’s invented langua... LLMs don't see individual characters, they see individual words.

lgas on April 11, 2023 [–]

Actually they see tokens, which are, usually, parts of words.

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