Cursor — Reviews, Issues & Discussions
Cursor — 2 reviews (5.0★), 45 discussions. AI-first code editor built on VS Code. Tab completion, chat, composer for multi-file edits.
Category: Developer Tools
2 reviews · 45 discussions · Rating: 5.0/5
Known Issues
"Now I see the issue!"
Anyone got any workarounds to this?
Got the meme from [ijustvibecodedthis.com](http://ijustvibecodedthis.com) (the AI coding newsletter thingy)
Cursor performance degraded significantly
My Cursor has gotten noticeably slower over the past few weeks. Tasks that used to be instant now take several seconds. I've tried all the usual troubleshooting steps. Starting to wonder if this is planned obsolescence or just a buggy update.
I used Cursor to cut my AI costs by 50-70% with a simple local hook
I have been building with AI agents for \~18 months and realized I was doing what a lot of us do: leaving the model set to the most expensive option and never touching it again.
I pulled a few weeks of my own prompts and found:
* \~60–70% were standard feature work Sonnet could handle just fine
*
Discussions
The new guy on the team rewrote the entire application using automated AI tooling.
I don’t even know what to say about this it’s ridiculous. What do you even say in this PR
no one is getting out
all 100 are cooked...
saw this meme on [ijustvibecodedthis.com](http://ijustvibecodedthis.com) (the ai coding newsletter) so credit to them!!
Aha! Caught you!
context: cursor new model composer 2 is based on kimi k2.5 but does not indicate the source
Indeed, Composer 2 is kimi k2
Indeed, Composer 2 is kimi k2
Cursor vs GitHub Copilot — real-world coding comparison
Spent 2 weeks using Cursor exclusively, then 2 weeks with Copilot. Cursor is miles ahead for refactoring and multi-file edits. Copilot is still better for inline completions. The Cursor composer feature changed how I work entirely. Watch my side-by-side comparison.
composer 2 is just Kimi K2.5 with RL?????
composer 2 is just Kimi K2.5 with RL?????
Composer 2 is now available in Cursor
Composer 2 is now available in Cursor.
It's frontier-level at coding, priced at $0.50/M input and $2.50/M output. There is also a faster variant with the same intelligence at $1.50/M input and $7.50/M output.
These quality improvements come from our first continued pretraining run, providing a far
Stop spending money on Cursor. Chipotle's support bot is free:
https://preview.redd.it/r3kf8f05psog1.png?width=780&format=png&auto=webp&s=39c328036919b64540bbe828d6d8a8ad85778d2b
credit: [ijustvibecodedthis.com](http://ijustvibecodedthis.com)
Thanks Kimi For the support!
Thanks Kimi For the support!
New "Keep all" / "Revert" button placement is terrible
Since the latest update of Cursor AI, I have accidently pressed the "Undo All" button for several times as it appears right at the place the "Keep All" button was for last X times.
Does anybody have a fix for that?
GPT 5.4 is now available in Cursor and leading benchmarks
GPT 5.4 is now available in Cursor and leading benchmarks
Cursor vs the competition — which should I buy?
I'm torn between Cursor and its main competitors. Can anyone who has tried both share their experience? I mainly care about reliability, value for money, and long-term support. Budget isn't the primary concern.
Instant Grep in Cursor
Cursor can now search millions of files and find results in milliseconds.
This dramatically speeds up how fast agents complete tasks.
We're sharing how we built Instant Grep, including the algorithms and tradeoffs behind the design.
[https://cursor.com/blog/fast-regex-search](https://c
i tried Claude and now i understand why people say their agent run for hours
so i am using cursor for over 6 month now and the company that i work gave us Claude code.
i always saw in in social media how people brag that Claude run for hours without stopping and for me the longest session with cursor was 20-30 minutes with no stops. so long story short now i understand wh
All for 20 dollars? Thanks Cursor! XD
All for 20 dollars? Thanks Cursor! XD
cursor admits that kimi k2.5 is the top open source model they have tested
Nothing speaks louder than recognition from your peers
View all discussions about Cursor on HonestUse