Hi All. I wonder if someone from cursor could shed some light on this. Ive been using cursor paid for a while now. Ive noticed the models seem to have gotten increasingly more “stupid” with code questions especially when it comes to any larger chunks of code. Using paid cursor I get these options …

I have a similar question: For cursor chat, does cursor-fast use gpt-4-0613 or gpt-4-1106-preview or gpt-4-0125-preview GPT-4 slow requests uses 0613? What about inline edit (ctrl-k) which base model does it use?

Would be great to get some clarity on this! Its the source of much frustration daily for me and I still find consistently that cursor-fast or gpt4 using cursor is not as intelligent as the preview models using my own keys.

Do you have an example of where using your own key gives you better answers? cursor-fast: a 3.5-level model that follows our cmd-k format a little bit better gpt-4: since a few weeks ago, has been all gpt-4-0125-preview

Could it be that when using your own API, your context length is 128k tokens but it’s only 8k when using cursor?

Just to clarify, you use 10k tokens always? But GPT4 turbo supports 128,000 did I understand that correctly? So do I understand that if I hit issues where cursor is struggling due to large chunks of code (where token size seems to be the cause) ill get better results going direct to https://platfor…

How can I use the 128k context in openai? never used my own keys, should try. I find the default model having a bit of hallucinations (suggesting non existent but ‘would make sense if it exists’ classes and functions as chatgpt does :sweat: ) I wonder if those other latest versions that work only th…

In the past week it has gotten so much worse! However, I’ve noticed ChatGPT is also suffering from serious comprehension issues. cursor-fast was fairly decent, but now it’s completely unreliable, struggles with the most basic asks even with small context being fed into it. gpt-3.5 the same issue, …

From what I understand, Cursor is currently using the GPT-4 0125 model, which, according to this article: URL , has become even worse. If you connect your own API key, you will have access to the older GPT-4 1106 model, which handles tasks better and hallucinates less. And yes, you can use your key w…

So cursor is using only 10k token context window? Because I also have a ChatGPT enterprise account which seems to use128k token context window. So not sure if I should better use the enterprise acccount for some things?

Why are the models on using your own keys so much better?

Discussions

arvid220u (Arvid Lunnemark) February 15, 2024, 10:26pm 6

No, we’re using 10k tokens regardless of model.

GPT-4 Turbo for Pro users

Just to be clear, does Cursor Pro use GPT4-0125 with 128k context window?

Gpt4-0, context size?

New GPT-4o-128k

What is the context size for gpt 4o mini?

Topic		Replies	Views
Just to be clear, does Cursor Pro use GPT4-0125 with 128k context window? Help	1	610	March 5, 2024
Why does Cursor seem "dumb" lately? Discussions	18	2450	December 19, 2023
It seems to me that the fourth model has become very stupid Bug Reports	20	1509	December 13, 2023
I don't get it.. What is advantage to paying Cursor AI vs using a ChatGPT 4 key? Discussions	13	8447	August 21, 2024
Which is cheaper: more Fast Requests or add own GPT-4 Turbo api-key? Discussions	3	887	October 12, 2024

Why are the models on using your own keys so much better?

Related topics