I suspect that the largest limiting factor for a competing model will be the dat... | Hacker News

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

		zamalek on Sept 12, 2024 \| parent \| context \| favorite \| on: Learning to Reason with LLMs I suspect that the largest limiting factor for a competing model will be the dataset. Unless they somehow used GPT4 to generate the dataset somehow, this is an extremely novel dataset to have to build.

j_maffe on Sept 12, 2024 [–]

They almost definitely used existing models for generating it. The human feedback part, however, is the expensive aspect.

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