Comment by meroes
5 days ago
It shows models need RL for any new domain/level of expertise, which is contrary to what the marketers claim about LLMs and potential for AGI.
5 days ago
It shows models need RL for any new domain/level of expertise, which is contrary to what the marketers claim about LLMs and potential for AGI.
No comments yet
Contribute on Hacker News ↗