nate

@pvncher wait this is good

Idk about this one guys

Composer 2 marks the one-year anniversary of our large model training efforts. Since then, we've built an exceptionally talent-dense team of ~40 people with some of the best researchers and engineers from the labs, academia, industry, and more heterogeneous backgrounds. And we are exclusively focused on coding. We don't care about models that can respond to emails, do your tax returns, or be your friend. Every FLOP, token, parameter, and researcher is entirely dedicated to software engineering.

@srush_nlp true

@_nateschmidt k a h u n a

c u r s o r b i i g

super cool to see composer keep on chugging during our experiments w/ a tiny context window

@edwinarbus liking this post to subscribe to tiramisu

I have perhaps liked one too many posts about tiramisu on here Now 1/5 posts on my timeline are tiramisu I am ok with it 👍👍

We're sharing a new method for scoring models on agentic coding tasks. Here's how models in Cursor compare on intelligence and efficiency:

Excited to announce that @cotoolai has raised a $7.4M seed round led by @a16z to build the agent operating system for security teams. Threat actors now scale with tokens. Campaigns that used to require a coordinated team can be run by a small group with the right model harness. Defense has been absorbing that hit with the same playbook and the same headcount. We built Cotool to make defense compound in the same way. Grateful to the team at @a16z, @ycombinator, @WndrCoLLC, @homebrew, and our angels from Okta, Ramp, Cloudflare, and others who've lived this problem firsthand. If you’re a security practitioner looking for more leverage in the AI age, come see how Cotool can help!

@maxpollard415 @cotoolai @a16z congrats!!

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.

@LDanilek @cursor_ai :lees-cursor:

Did you know you could make a grid of agents in @cursor_ai ? I've been running 3 agents nonstop, and there's still room for a browser, terminal, and code browsing. Set it up by dragging tabs around

Have been using @cursor_ai cloud agents to ship some of the smaller features and bug fixes for the past few weeks. Think the experience is >> all else atm. the video / screenshot proof is so satisfying (E.g. file download support feature here)

I've run hundreds of these and it still feels like I'm in the future each time

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.

@DanielPrevoznik @milichab @cursor_ai Agents > Default Location 🙏

@milichab @cursor_ai where exactly?!

plz @cursor_ai just let me config to default opening all new agent chats as editor

love having a handful of these running throughout the day while I do focused work. excited for folks to try them!

We've raised limits for Auto and Composer 1.5 for all individual plans. Individual plans now have 3x usage of Composer 1.5 versus Composer 1. For a limited time (through February 16), we're increasing that to 6x.

Composer 1.5 is now available. We’ve found it to strike a strong balance between intelligence and speed.

@JasonBud this is the way

my daily driver (high fast)