> Where a human can understand a concept without words, an LLM plainly cannot. I... | Hacker News

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

zahlman 25 days ago | parent | context | favorite | on: Show HN: The load-bearing vocabulary of Claude

> Where a human can understand a concept without words, an LLM plainly cannot.

If we accept that the LLM can "understand" at all, why would we reject the possibility of this understanding living in "latent space", before tokens are output?

chrisjj 25 days ago [–]

Because these modeks have no latent space. They work by tokens and nothing else.

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