All the Hard Stuff Nobody Talks About When Building Products with LLMs

Re:All the Hard Stuff Nobody Talks About When Building Produ... by kristjansson on Saturday May 27, 2023 @03:40PM (#36097546)

If a user is waiting on the response, you basically have to stream the result instead of waiting on the entire completion.

[ Parent | on HN ]

Re:All the Hard Stuff Nobody Talks About When Building Produ... by joelm on Saturday May 27, 2023 @03:50PM (#36097632)

Yea, that is probably a better solution. Not an easy one to refactor into at the moment though.

[ Parent | on HN ]

Re:All the Hard Stuff Nobody Talks About When Building Produ... by ukuina on Saturday May 27, 2023 @10:54PM (#36100716)

There's no real benefit to streaming if you are planning to use the LLM output downstream (say, in a SQL query). LLM latency is a major annoyance right now, whether locally-hosted or cloud-based.

[ Parent | on HN ]