zlacker

[parent] [thread] 1 comments
1. trc001+(OP)[view] [source] 2025-06-07 14:37:51
Uh, the bellman equation was first used for control theory and is the foundation of modern reinforcement learning... so wouldn't that imply LLMs "come from" control theory?
replies(1): >>fc417f+L21
◧
2. fc417f+L21[view] [source] 2025-06-08 01:35:42
>>trc001+(OP)
Is the training algorithm the AI or is the model that you get at the end the AI?
[go to top]