RL doesn't need that much static data, it needs a lot of "good" tasks/challenges... | Hacker News

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

vicentwu on Jan 27, 2025 | parent | context | favorite | on: Nvidia’s $589B DeepSeek rout

RL doesn't need that much static data, it needs a lot of "good" tasks/challenges and computation.

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