Re:Creating AI assistant with GPT and Ruby and Redis using e...
by joe_the_user on Wednesday April 26, 2023 @10:01PM
(#35722395)
I'd say:
Yes - embedding are a hack:
No - there won't anything like a "real API" unless there's a new discovery or a shift in the way LLMs are constructed. It's not theoretically impossible but there's no clear way to get guaranteed results from present day LLMs, all they do output guesses from their input text (combining prompt text and then user text).
Yes - embedding are a hack:
No - there won't anything like a "real API" unless there's a new discovery or a shift in the way LLMs are constructed. It's not theoretically impossible but there's no clear way to get guaranteed results from present day LLMs, all they do output guesses from their input text (combining prompt text and then user text).