But can we say that the LLMs are consciously designed? AFAIK nobody really understands why they work.
Whether they are or not is irrelevant to the difference- there is still an explicit division between training and inference, with reinforcement of the statistics of the training set.
alt Hacker News
Whether they are or not is irrelevant to the difference- there is still an explicit division between training and inference, with reinforcement of the statistics of the training set.