Well, yes, but remember there is the reinforcement learning that is applied afte... | Hacker News

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

altcognito 64 days ago | parent | context | favorite | on: China’s open-weights AI strategy is winning

Well, yes, but remember there is the reinforcement learning that is applied after, and the system prompts that will bend the results.

lossolo 64 days ago [–]

Yeah, agree on both points. You can embed any bias you want using RL, regardless of training data.

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