←back to thread

A non-anthropomorphized view of LLMs

(addxorrol.blogspot.com)
475 points zdw | 1 comments | 06 Jul 25 22:26 UTC | HN request time: 0.818s | source
Show context
rf15 ◴[07 Jul 25 12:52 UTC] No.44489874[source]▶
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.
replies(2): >>44489893 #>>44491528 #
1. ethan_smith ◴[07 Jul 25 15:43 UTC] No.44491528[source]▶
The chat interface is a UX compromise that makes LLMs accessible but constrains their capabilities. Alternative interfaces like document completion, outline expansion, or iterative drafting would better leverage the full distribution of the training data while reducing anthropomorphization.