I am opeing this topic in the hope to raise more awareness on how bad Cursor seems to perform lately…
I just tried to de-bug a 100 line python script using Claude 3.5 and it keeps getting it wrong and curcles arround.
Cursor used to be good… now I feel it is getting worse by the week…
Like this I wont be using it for much longer
Haven’t used Cursor yesterday but since today I also encounter really bad quality answers (using Claude 3.5). Does anyone know the cause? Trying gpt-4o now…
I was very skeptical of this theory until it happened to me the 3 days ago with a seemingly easy enough request for sonnet 3.5. I tried 3 times in the composer (restarting the session, new reformulated prompt) and they all failed. It was changing code that it wasn’t supposed to.
I fired up VS Code and gave the task to copilot agent with sonnet 3.5, 2 prompts later it was done and working.
I heard that Microsoft host their own instance of Sonnet, so they don’t depend on the API from Anthropic. So now when Sonnet 3.5 underperform, I no longer fight it and just switch to copilot.
Yep, idk what’s happening, but definetly, Cursor is becoming useless… Went from using it the whole time, to… being tired of rolling back and starting from scratch.
My theory is:
Which leads to the current situation…
It feels like something they’ve introduced to reduce the load on the AI and maybe save on context as well
Even claude has gotten a bit lazier about reading existing files
although waiting for slow requests seems to have gotten better (?) so maybe that’s the tradeoff 
Its completely useless right now. It won’t accomplish anything.
That’s exactly the point… It’s not even about a “tradeoff”.
Not about “not that great”, “reduced performance”, or even “lower your expectations”.
It’s simply… useless, literraly, not figuratively.
It is completely useless on Jupyter notebooks. It wasn’t that good to begin with, but now it just suggests random things.
A bunch of MS bots?
If it is completely useless go use something useful
OMG Yes! I switched to Cursor after using CodeBuddy for a while but getting annoyed that CodeBuddy just kept making the same stupid mistakes over and over again. Cursor seemed like magic.
But now, I don’t know why, but it really seems to be getting dumber. I have wasted like $10 today just fixing a few simple things that, admittedly, I should probably just be able to fix myself. But I’m stubborn. I even use ChatGPT to help me explain to Cursor what I want to do to because my original version gets more and more riddled with typos and obscenities as I try for the 20th time to get it to so something. It’s getting really expensive.
It’s failing to find the files it should use and is constantly making new ones. It’s ignoring the cursorrules file. It’s ignoring my naming conventions.
I should just take the day off. It’s been off to a really frustrating start today trying to get Cursor to help me fix some fairly simple and straightforward things in my app. I even through the hassle of writing out a bunch of different queries to help it understand how the data is structured and it just didn’t get it.
And dev container are broken again. 
Same here. It just started speaking nonsense since a couple of days ago no matter using what model. Giving ridiculously wrong responses almost half of the time. Disappointed.
I’m glad I’m not the only one experiencing this. I started a new project a few weeks back. In the last week or so Cursor is almost completely unreliable.
Just a few random examples:
I’m afraid now to resume work on an App I have been developing before this started to happen and am going to shut cursor down for a few days.
Shouldn’t the Cursor team respond to this situation?
ohh, not only me! its terrible!!!
I downloaded 0.46 and that got rid of the Composer. The new agent they implemented doesn’t change any files, doesn’t know any files, its useless. Had to uninstall and revert back to 0.45…
Recently, Cursor’s new update has been a problem. It was really stupid than before. I provide file/folder but it still says: “I can’t read”, “can’t find it”, it has lost Handle Source?
I’ve had a similar situation. This could be major user error on my end but I also noticed it stopped overlaying “suggested changes” automatically and now just populates them and requires me to click “accept changes” manually for each snippet (often in the wrong file).
Does anyone know how to fix this or why?
A few issues i’ve experienced;
Anyone else seeing these issues?
For Claude 3.5 users, I have to say that maybe Anthropic degraded quality of 3.5 before releasing 3.7…
Now with 3.7, it’s way better 