It would be great to see more focus on Chinchilla's result that most large model... | Hacker News

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

		benlivengood on Oct 7, 2022 \| parent \| context \| favorite \| on: The AI Scaling Hypothesis It would be great to see more focus on Chinchilla's result that most large models were quite undertrained with respect to optimal reduction in test loss.

andreyk on Oct 7, 2022 [–]

agreed, we did not discuss that sufficiently

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