Michael Truell

Composer 2 is out! Cursor is an example of a new type of company, not a pure app maker and not a model provider. Our aim is to build the most useful coding agents by combining the best API models and our domain-specific models.

@mil0theminer We wrote about it here! cursor.com/blog/cursorben…

To this day we still don’t know what “cursorbench” is

Automations already run thousands of times per day inside our own codebase! They power self-healing CI, auto-approving PR flows, highly-compute-intensive security review, and a team-wide memory system. One small step toward a self-driving codebase...

@snowmaker I think you might be surprised by cursor.com/onboard.

Writing code by hand was walking Using Cursor was getting in a car Claude Code in an existing repo is an airplane Claude Code in a new repo is getting in a rocket

@littmath Full solution here: drive.google.com/file/d/1wqNqUo…

Thanks to the First Proof team for setting these problems, and to Ingo Althöfer, Tony Feng, Daniel Litt, Yang Liu, and Jan Vondrák for helpful comments. Resources: - First Proof: 1stproof.org - Blog post by @littmath: daniellitt.com/blog/2026/2/20… - OpenAI's solution: x.com/merettm/status… - DeepMind's solution: x.com/lmthang/status…

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.

@bdc Welcome bdc!!

Back to work.

@karpathy One surprising fact: despite requiring a large behavior change, we're seeing the beginnings of a rapid diffusion of cloud agents (perhaps "agent teams" in the Karpathy taxonomy). Cloud usage in Cursor is up ~6x in the past two months and climbing.

Cool chart showing the ratio of Tab complete requests to Agent requests in Cursor. With improving capability, every point in time has an optimal setup that keeps changing and evolving and the community average tracks the point. None -> Tab -> Agent -> Parallel agents -> Agent Teams (?) -> ??? If you're too conservative, you're leaving leverage on the table. If you're too aggressive, you're net creating more chaos than doing useful work. The art of the process is spending 80% of the time getting work done in the setup you're comfortable with and that actually works, and 20% exploration of what might be the next step up even if it doesn't work yet.

@rsd4444 cursor.com/onboard

@mntruell How do I try it out myself?

We just launched demos! I think it’s a glimpse at a post-code future. Over a third of our PRs are now created autonomously with this feature.

Jobs called computers "bicycles for the mind" -- tools we could shape to our will. But they never were. Until now. Every morning an agent preps me for my day -- calendar, news, last 24hrs of Slack -- in a personal podcast. I made it by asking. Same for hundreds of other things. Launching @dreamer in beta today. That 🧠 bicycle, finally. dreamer.com

@JoshuaKushner Congratulations Josh!

We are pleased to announce the close of Thrive X. Exceeding $10 billion, Thrive X comprises $1 billion designated for early-stage investments and $9 billion designated for growth-stage investments. We do not view this as a milestone, but as a commitment to the long work ahead. We view Thrive as a company. Our product is partnership - the willingness to commit deeply to a small number of founders, and to stand with them through momentum and adversity. This is the discipline we bring to our work, and the responsibility we accept when founders partner with Thrive. We do not hedge. Concentration demands loyalty to the founders and missions we back. In this moment, exposure alone is not a strategy. Judgment without commitment is not enough. Advantage will accrue to those who choose deliberately, commit deeply, and endure through difficult moments. Thrive was founded to be an enabling technology for the world we want to see. We are deeply aware that we are not the main character. The founders that we are fortunate enough to partner with are the artists. Our role is to help create the conditions where great work can come to life. We take a long view grounded in the belief that category-defining companies tend to create structural compounding advantages over long arcs. This fund reflects the continuity of our approach and the ways our work has deepened alongside the founders we support. We are grateful for the trust our Limited Partners place in us, and for the opportunity to work alongside those who are building with purpose, integrity, and courage. thrivecap.com/thrive-x

@SIGKITTEN Maybe sometime in the future! We've published bits of our tab work, e.g. cursor.com/blog/tab-rl

@mntruell hey, could u guys open-source something around your Tab model? idk, pipeline/model/blog post/anything Since we're all going full-vibe would be great to get a glimpse of the awesome Tab model u guys made

You can now easily give Cursor access to your knowledge bases, deployment environments, observability suite, internal tools, and design files. Ask it to figure out an error by scanning through Datadog, hunt down runbooks in Notion, deploy to AWS, or replicate a mock from Figma. Much of this was possible before, but it was too hard. Now it feels like installing an app! You can configure plugins for your whole team too.

We've been delightfully surprised to see that pull requests from long-running agents have higher merge rates, while being ~an order of magnitude more ambitious.