From my experience there's definitely context beyond the current set of LLM stat... | Hacker News

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

		razodactyl on Nov 22, 2023 \| parent \| context \| favorite \| on: Greg Brockman quits OpenAI From my experience there's definitely context beyond the current set of LLM state. It's how they're able to regurgitate facts or speak at all.

mlyle on Nov 22, 2023 [–]

> regurgitate facts or speak at all.

Most of that is encoded into weights during training, though external function call interfaces and RAG are broadening this.

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