Introducing the Cursor Developer Habits Report.
We’re sharing some of our findings on how software development is changing.
It’s based on the most comprehensive dataset on AI coding in the world, across all model families.
the most used skill internally at cursor right now
/thermo-nuclear-code-quality-review
- deletes complexity instead of moving it
- blocks files over 1k lines
- flags thin wrappers and leaked logic
- rejects PRs that work but make code messier
Introducing Composer 2.5, our most powerful model yet.
It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions.
For the next week, we’re doubling the included usage of the model.
cursor design mode + remotion is actually insane
everything in remotion is code, so you can annotate changes directly on the video and cursor just updates it. having a lot of fun with this
here's 15 minutes of me improving the agent swarm video
Introducing /multitask in the new Cursor 3 interface.
Cursor can now run async subagents to parallelize your requests instead of adding them to the queue.
For already queued messages, you can ask Cursor to multitask on them instead of waiting for the current run to finish.
GPT-5.5 is now available in Cursor!
It's currently the top model on CursorBench at 72.8%.
We've partnered with OpenAI to offer it for 50% off through May 2.
Fantastisk Cursor-meetup i går! Takk til alle som kom, og de som holdt foredrag, Mesh Oslo og Ivana Piljic for bildene. Mange gode innspill om Cursor, AI-agenter og bygging i praksis. Neste gang: Cursor Cafe? 🤔
We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
We believe Cursor discovered a novel solution to Problem Six of the First Proof challenge, a set of math research problems that approximate the work of Stanford, MIT, Berkeley academics. Cursor's solution yields stronger results than the official, human-written solution.
Notably, we used the same harness that built a browser from scratch a few weeks ago. It ran fully autonomously, without nudging or hints, for four days.
This suggests that our technique for scaling agent coordination might generalize beyond coding.