Glass was a codename while the UI was in early alpha with testers. It redirects to download now because there is no special link anymore. It's just part of Cursor 3 itself.

I'm an engineer at Cursor, can try to clarify questions here.

> I wish they'd keep the old philosophy of letting the developer drive and the agent assist. Even when I'm using AI agents to write code, I still find myself spending most of my time reading and reasoning about code.

We very much still believe this, which is why even in this new interface, you can still view/edit files, do remote SSH, go to definition and use LSPs, etc. It's hard to drive and ship real changes without those things in our opinion, even as agents continue to get better at writing code.

> I'm hoping in this new UI in v3 I can still get that experience (maybe it's just hidden behind a toggle somewhere for power users / not shown off in the marketing materials).

This new interface is a separate window, so if you prefer the Cursor 2 style, that continues to exist (and is also getting better).

Once I downloaded it, it made sense. The blog post almost made me cancel my subscription because it seemed to get rid of the IDE entirely.

Great, glad to hear that! Stoked to kick the tires on Cursor 3. Thanks for confirming, leerob!

> We very much still believe this

That's good to hear, I might have jumped a little too quickly in my opinion. It's a bit of a Pavlovian response at this point seeing a product I very much love embrace a giant chat window as a UX redesign haha.

I would love to see more features on the roadmap that are more aligned with users like us that really embrace the Cursor 2 style with the code itself being the focal point. I'm sure there's a lot you can do there to help preserve code mental models when working with agents that don't hide the code behind a chat interface.

We used a Kimi base, with midtraining and RL on top. Going forward, we'll include the base used in our blog posts, that was a miss. Also, the license is through Fireworks: https://x.com/Kimi_Moonshot/status/2035074972943831491

Thanks for sharing this, I saw Cursor are committed to publishing this now which is great to see.

Are there other coding benchmarks we should include next time? We included Teminal-Bench 2.0 and SWE-bench Mulitilingual.

We don't plan on reporting SWE-bench Verified, for similar reasons to OpenAI: https://openai.com/index/why-we-no-longer-evaluate-swe-bench...

You can disable this if you want, it's under "Inline Diffs" in the Cursor settings.

We've found it to be a strong mix of speed and intelligence. It scores higher than Sonnet 4.5 on Terminal-Bench 2, maybe we will post more on this later.

Yeah, please do. Because when the AI labs you are competing with are posting extensive benchmarks and you just say "well we used our own internal benchmark" it is a bit sus, especially given the fact that the price has tripled.

You should! This blog post doesn't really give any reason to use it besides "it's better on Cursor's internal benchmark". A full model card would be great.

The way benchmarks for Composer have been presented since v1 feels unusually cautious. To users, that reads as “the model isn’t very good”.

There's a setting to turn this off if you prefer (Cursor Settings > Agent > Attribution).

ah yes thank you very much that did work

still not great in my opinion sadly i think this will likely get worse and perhaps never get better

commit messages as marketing materials and 'kpi's is an anti-pattern i would have preferred to avoid

> in particular the extra layer of diff-review of AI changes (red/green) which is not integrated into git

We're making this better very soon! In the coming weeks hopefully.

That's great news.

I see in your public issue tracker that a lot of people are desperate simply for an option to turn that thing off ("Automatically accept all LLM changes"). Then we could use any kind of plugin really for reviews with git.

(I work at Cursor) We have all these! Plan mode with a GUI + ability to edit plans inline. Todos. A tool for asking the user questions, which will be automatically called or you can manually ask for it. Hooks. And you can use Opus or any other models with these.

> The JS engine used a custom JS VM being developed in vendor/ecma-rs as part of the browser, which is a copy of my personal JS parser project vendored to make it easier to commit to.

https://news.ycombinator.com/item?id=46650998

It looks like there are two JS backends: quickjs and vm-js (vendor/ecma-rs/vm-js), based on a brief skim of the code. There is some logic to select between the two. I have no idea if either or both of them work.