News for hackers. Stuff that matters.

A comment on Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?. Parent comment

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by ianbicking on Wednesday May 31, 2023 @02:18PM (#36141768)
People here need to learn to chill out and use the API. The GPT API is not some locked down cage. Every so often it'll come back with complaints instead of doing what was asked, but that's really uncommon. Control over the system prompt and putting a bit of extra information around the requests in the user message can get you _so_ far.

It feels like people are getting ready to build castles in their mind when they just need to learn to try pulling a door if it doesn't open the first time when they push it.

[ Parent | on HN ]
Re:Ask HN: Is it just me or GPT-4's quality has significantl... by com2kid on Wednesday May 31, 2023 @03:25PM (#36142875)
The API chat endpoint dramatically changes its responses every few weeks. You can spend hours crafting a prompt and then a week later the responses to that same prompt can become borderline useless.

Writing against the ChatGPT API is like working against an API that breaks every other week with completely undocumented changes.

[ Parent | on HN ]
Re:Ask HN: Is it just me or GPT-4's quality has significantl... by krainboltgreene on Thursday June 01, 2023 @03:51AM (#36148544)
> The API chat endpoint dramatically changes its responses every few weeks. You can spend hours crafting a prompt and then a week later the responses to that same prompt can become borderline useless.

Welcome to statistical randomness?

[ Parent | on HN ]
Re:Ask HN: Is it just me or GPT-4's quality has significantl... by rainy59 on Thursday June 01, 2023 @12:02PM (#36153090)
... with temperature = 0
[ Parent | on HN ]
Re:Ask HN: Is it just me or GPT-4's quality has significantl... by com2kid on Thursday June 01, 2023 @07:49PM (#36159036)
No, these are clear creative differences.

I submit the same prompt dozens of times a day and run the output through a parser. It'll work fine for weeks then I have to change the prompt because now 20% of what is returned doesn't follow the format I've specified.

A couple months ago the stories ChatGPT 3.5 returned were simple, a few sentences in each paragraph, then a conclusion. Sometimes there were interesting plot twists, but the writing style was very distinct. Same prompt now gets me dramatically different results, characters are described with so much detail that the AI runs out of tokens before the story can be finished.

[ Parent | on HN ]
Re:Ask HN: Is it just me or GPT-4's quality has significantl... by Madmallard on Wednesday May 31, 2023 @09:29PM (#36146647)
This is misinformation
[ Parent | on HN ]