This is soooo much more exciting than the "put 100M tokens in the context window... | Hacker News

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

		skeptrune on Feb 16, 2024 \| parent \| context \| favorite \| on: Training LLMs to generate text with citations via ... This is soooo much more exciting than the "put 100M tokens in the context window" idea

bugglebeetle on Feb 16, 2024 | [–]

I would say the large context sizes with the ability to reliably cite said context is the best possible outcome.

amelius on Feb 16, 2024 | [–]

ELIZA was so much more exciting than the "put 100B artificial neurons on a GPU" idea.

;)

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