[victorvosk]

I don't care what the official line is, something changed with it. It might be the same model but the way it answers questions and the content of those answers is much more dubious now. I think how it manages its conversation context was gimped in the web chat version. I find it routinely completely forgetting things in longer conversations.

[Stagnant]

It is the text generation speed that got me suspicious. It seems like ChatGPT's GPT4 suddenly got 2-3 times faster at generating text, while the API GPT4 still generates the text at the same pace as it always has.

[hickelpickle]

I was using it to experiment lazily with machine learning and midi generation via CNN-LSTMs and noticed it happening in the middle of a chat with it. The context wasn't that long and it was providing excellent insights, then randomly started telling me how to make a music game in python and lost all previous context. I tried starting a new chat and adding the back context,had a good bit of code I was providing for context, and it could hardly keep track of the provide code context over the course of a few simple questions/changes, when before it had no problem and would actually surprise with drawing from long past context relevantly. After what ever happened it would randomly assume karras was being used if having not been provided any pytorch specific code for a few messages.

API doesn't have these issue, or didn't a week ago when I was using it often, but something happened with the web model, which I guess is understandable, as the main reason I was using it vs the API was cost savings.

[jonplackett]

I was thinking how I could optimise for longer conversations and the most obvious thing seemed to be to somehow summarise the conversation ever X messages and ask it to save what it things is important isn’t them.

If they’re doing something like this that would probably explain it.

[93po]

Copilot censored its response to my question about linked lists yesterday. Ridiculous.