maybe the comment was about safety related training leading to performance loss. Sebastien used the "Unicorn benchmark" to visualize such nerfing. Watch his talk at timestamp 26:22. Ref: https://youtu.be/qbIk7-JPB2c?t=1582
None of these models are even close to GPT 3.5, let alone GPT4.
*the api wasn't nerfed. ChatGPT4 was most certainly changed
The comments seem to conclude that it was actually nerfed just not the API.
It most certainly was, despite what anyone from openai says. It’s not working the same.
It most definitely was. The chat output of GPT4 is much faster now and much worse quality. If you go in the playground and use the March 14 api (as opposed to the default GPT4 API) it is high quality and slow. Yes, there are two GPT4 API endpoints .
Here's the discussion for that benchmark with some values.