News for hackers. Stuff that matters.

A comment on Measured typing latency of popular terminal emulators. Parent comment

Re:Measured typing latency of popular terminal emulators by LeoPanthera on Wednesday May 03, 2023 @07:30PM (#35809249)
GPT doesn't work that way. Any such shell would have to send a GPT request for every single keystroke, and you'd hit the API ratelimit very quickly. It would also be very expensive.
[ Parent | on HN ]
Re:Measured typing latency of popular terminal emulators by LanternLight83 on Wednesday May 03, 2023 @09:32PM (#35810202)
Maybe a solid use case for local models are they're optimized for consumer hardware-- someone clever could preserve as much context as possible between requests
[ Parent | on HN ]
Re:Measured typing latency of popular terminal emulators by throwaway280382 on Thursday May 04, 2023 @02:57PM (#35820405)
Well, eventually, better models will be made and they can be used locally
[ Parent | on HN ]