OpenAI postmortem – Unexpected responses from ChatGPT

Re:OpenAI postmortem – Unexpected responses from ChatGPT by laborcontract on Wednesday February 21, 2024 @09:51PM (#39462596)

The explanation is definitely unsatisfying. If I had to guess it was an issue with quantization.

OpenAI moves so quickly with their product and doesn't seem to be shy about quickly pushing changes to prod. There are too many times to count that, using ChatGPT, I've seen the frontend changing before my eyes or seen responses change as backend modifications are pushed.

On one hand it's refreshing to see their lack of aversion to push changes. On the other hand, it leads to probably one of the most unpredictable experiences I've had using any consumer product.

[ Parent | on HN ]

Re:OpenAI postmortem – Unexpected responses from ChatGPT by p10_user on Wednesday February 21, 2024 @10:42PM (#39462974)

Does the API offer "fixed" models that don't change? I was under the impression they did.

[ Parent | on HN ]

Re:OpenAI postmortem – Unexpected responses from ChatGPT by Rastonbury on Thursday February 22, 2024 @02:30AM (#39464244)

I find that the most annoying and borderline unethical, hiding changes and nerfs behind the fact the output is probalistic especially when I'm paying the same amount for the product and others are paying for and using it in production. As many have mentioned, GPT-4 ability to code is not the same as 6-8 months ago

[ Parent | on HN ]

Re:OpenAI postmortem – Unexpected responses from ChatGPT by jorticka on Thursday February 22, 2024 @03:04AM (#39464463)

So stop paying then.

[ Parent | on HN ]

Re:OpenAI postmortem – Unexpected responses from ChatGPT by MVissers on Thursday February 22, 2024 @05:33AM (#39465308)

Stop paying for chatgpt and use platform.openai.com instead to pick your model for consistency.

I’m still using the original gpt-4-3.14 model.

[ Parent | on HN ]