zlacker

[return to "A non-anthropomorphized view of LLMs"]
1. rf15+Kl1[view] [source] 2025-07-07 12:52:08
>>zdw+(OP)
It still boggles my mind why an amazing text autocompletion system trained on millions of books and other texts is forced to be squeezed through the shape of a prompt/chat interface, which is obviously not the shape of most of its training data. Using it as chat reduces the quality of the output significantly already.
◧◩
2. semant+3m1[view] [source] 2025-07-07 12:54:45
>>rf15+Kl1
What's your suggested alternative?
[go to top]