2 results for "d1cf8b9c8c7ce0df2060a5bf4a0c3c34"
>>106161551
>Posting dipsy
>>106121322
I don’t know why more people don’t get this. the sheer size of the datasets drives writing to an average, vs. The Superior. Theyre not using the best texts, they’re using everything.
I think the way it’ll be healed, eventually, is the ability to train a model (in some sense) around a much smaller corpus of just The Superior (whatever that is) and have it reply in that manner.