building @cursor_ai and cursor.com/marketplace/curso…. @reactjs compiler core team. prev @meta @netflix

Joined September 2014
350 Photos and videos
Pinned Tweet
May 25

47
109
1,128
269,064
cya there!
See you at Cursor Compile next Tuesday in SF! I'll be talking with @levelsio about retro computing, building your ideas, lifting, the perfect steak, and more.
3
38
4,227
Jun 11
rewrites are good actually
8
6
156
11,516
lauren retweeted
We're training the next version of Composer... with Composer! The model is always learning from itself. This kind of "recursive self-improvement" might sound new, but it's been happening for many months! For example, training big models requires creating *lots* of data for RL - essentially games the model plays to improve at any task you can grade. The newest models can configure their own environments to make those games playable (auto-installing dependencies, fixing broken setups). Composer 2 was *dramatically* better at this than version 1. So the better the model gets, the better it gets at creating the conditions to train its successor. Each generation unlocks capabilities the previous one didn't have! So cool. x.com/cursor_ai/status/20521…

We use previous generations of Composer to train future ones. Our autoinstall system has earlier Composer models set up dev environments for RL training. That way, the next generation can focus on learning to solve harder problems. cursor.com/blog/bootstrappin…
129
101
2,200
193,509
Jun 11
phew im still a real developer
In 2026, you are not a real developer if you don't write 100k-line PRs
12
147
33,824
Jun 11
i broke a lot of stuff too 🫪 sorry team
4
31
1,823
lauren retweeted
Cursor’s code review agent is now over 3x faster, 22% cheaper, and finds 10% more bugs. You can also use /review to run Bugbot locally to catch and fix issues before pushing code.
99
138
2,400
166,023
Jun 10
pstack fable goes hard
6
68
7,201
lauren retweeted
Claude Fable 5 is now available in Cursor. It sets a new state of the art on CursorBench at 72.9%, 8 points above the previous best.
261
448
6,069
1,173,909
lauren retweeted
We've added a new harness! Cursor Composer 2.5 is live in Conductor. It's fast, precise, and cost-efficient. And when I say fast I mean _really_ fast. Excited to hear your thoughts!
56
28
677
119,152
Jun 8
the thing about loops is that you need to build trust first. a low trust loop is just a waste of tokens. and if you don't apply engineering taste, the slop really compounds. but you can become a quality loop enjoyer too with pstack as a starting point: github.com/cursor/plugins/tr… use these skills to write automations that automatically triage, repro, fix, and verify their own work while you touch grass. use them to prototype new ideas and refactor your code and trust that they'll do things the right way

8
5
77
11,755
Jun 8
i dont even write loops anymore my agents just read my mind while i phase shift into higher dimensions
24
26
366
26,063
Jun 7
see you there!
cafe cursor LA next month! july 15th - come meet @cursor_ai team, get credits and build some great coffee 💛
2
1
48
5,113
lauren retweeted
pstack has quickly taken over as the most dominant skill I use in claude code. It's so great and reliable
May 28
really like this model! try it out as your main agent in cursor along with pstack skills
1
6
2,347
lauren retweeted
what if you could just talk to a 1987 nes cartridge i just turned the @cursor_ai sdk into a nes rom hacker you describe a mod in plain english → agent searches the binary, proposes a byte patch, emulator hot-reloads in <1s "infinite lives" "give me the laser" "keep weapons after death" all just work s/o @poteto pstack is goated cc @ericzakariasson @leerob
15
9
81
9,978