If you go far enough in a field, you start to recognize areas where your personal opinion differs from the “best practices” usually recommended.I think by design an LLM can’t do that. It’s built to reflect the distribution of the knowledge it has been trained on.
surely the LLM can do that. It is RL'd against some reward, if the known strategies are clearly suboptimal with easy improvement, it'll find it most likely
jimbokun · · focus · HN ↗
I think by design an LLM can’t do that. It’s built to reflect the distribution of the knowledge it has been trained on.
Davidzheng · · focus · HN ↗