Would be cool if we could get the option to choose to use slow requests. There are times when I want to tweak just a few lines or where speed isn’t important. In these situations, using a fast request feels like overkill, and I often find myself hesitating, wondering if it’s worth consuming one of my limited fast requests. I understand I could use GPT-3, but I don’t really consider it a good alternative to 4 in most situations.
Not sure how your backend works, but it might even help with performance on your end if more people choose to use the slower version?
Thank you for the consideration.
PS: any news regarding GPT-4 Turbo. Would love some bigger context.
+1 for this idea, especially since something seems to have gone wrong with my “fast request” accounting over the last month. it would be great to be able to save them for when i need them.
Yes, I’ve been looking forward to this for quite some time. It would be absolutely awesome and significantly enhance my experience with Cursor! I’ve noticed the Cursor team discussing the possibility of such a feature, but unfortunately, there haven’t been any concrete developments yet.
++++1
I’ve had Cursor for a few days and already ate through a couple of hundred fast requests. I was under the impression that I’d have to change to the fast option, and that the default were the slow ones.
does a dev want to clarify what ‘cursor-fast’ is? vs. gpt-4 those are the only options I see in the Linux AppImage version. Why use different terminology from your documentation? I am inclined to think cursor-fast is some internal model you have rather than openai.
I hope they’re working on this. I would really like to “save” my fast requests for some more complex features I’m working on, and continue using slow ones for assists.
Have there been any updates regarding this? I’d like to be able to use slow on non-mission critical tasks, and save up my fast requests for time sensitive tasks/when I really need them.
Just throwing my hat in the ring but yes, I also am eating through my fast requests real quickly and had to unsub from Cursor because it wasn’t worth it over Phind.
And don’t get me wrong, I really, REALLY love cursor, but I can get an, albeit less well implemented, web-enabled Claude3.5 that can change my code, 500 requests per DAY instead of per month, at $20…
I calculated, if I really want to top up on fast requests, at the rate I am working, I’d need to spend $60 per month, which is a bit much IMO even with all the benefits… Cursor is amazing, but it’s not $40-more-expensive-than-phind-amazing
I’d really either need way more fast requests, or have a way to use the slow ones at will
Phind is not a good comparison for things like this, theres a ton of things that cursor is leveraging compared to the phind, its not really comparable imho and their value is quite different, you’re talking about Phind like someone who talks about ChatGPT where $20 a month is reasonable.
bu yes the option for the slow toggle/fast toggles would come in handy.
Need this implemented. I’m running out of fast queries so fast, and I don’t even need them all the time… I just need to be prioritized if there is a queue, but if the servers are not overloaded, why would I spend one of my prioritized queries?
I already thought this feature would be there before I bought it. I think this could be a sales strategy but if not I definitely think this feature should be added.
I already thought this feature would be there before I bought it. I think this could be a sales strategy but if not I definitely think this feature should be added.
Yeah, I thought this too when I subscribed over one year ago
