GPT-4 is not getting worse (tests and a long rant)

Re:GPT-4 is not getting worse (tests and a long rant) by moonchrome on Saturday September 16, 2023 @06:44AM (#37533652)

I think they probably finetuned that because it used to be the other way around and it was pretty bad UX to wait 1 min to apply a function change to a class or stuff like that.

[ Parent | on HN ]

Re:GPT-4 is not getting worse (tests and a long rant) by wouldbecouldbe on Saturday September 16, 2023 @06:55AM (#37533685)

Yeah sometimes you want it but sometimes you dont. I think they are enforcing to save resources

[ Parent | on HN ]

Re:GPT-4 is not getting worse (tests and a long rant) by jw1224 on Saturday September 16, 2023 @07:06AM (#37533734)

Are you using the API, or just the ChatGPT UI? Do custom instructions/system messages help at all?

Saving resources like this seems okay(ish) for general-purpose ChatGPT, as they'd know there's a human who can interpret the abridged output. But for API-driven requests this would be pretty terrible, and makes it far harder to develop with.

[ Parent | on HN ]

Re:GPT-4 is not getting worse (tests and a long rant) by wouldbecouldbe on Saturday September 16, 2023 @08:06AM (#37534093)

no the UI, where I ask it to "Please write out entire code with skipping parts."

[ Parent | on HN ]

Re:GPT-4 is not getting worse (tests and a long rant) by nomel on Saturday September 16, 2023 @01:39PM (#37536859)

ChatGPT 3 or 4? Try the playground. I’ve had much better luck with system prompts.

[ Parent | on HN ]