Viewing profile — leerob

You can read our full technical report here: https://cursor.com/blog/composer-2-technical-report

(I work at Cursor) We score well on Terminal-Bench and SWE-bench Multilingual. DeepSWE, not so great yet, as it's more for very long-horizon tasks. We're planning to include more p…

(I work at Cursor) When Composer 2.5 launched, we initially scored very competitively on AA's composite benchmark. I believe 3rd place overall. They have recently updated to use De…

(I work at Cursor) CursorBench includes many evals from actual engineering tasks from the Cursor team, which include our private codebase. This codebase is held-out from training s…

Will do. On it.

(I work at Cursor) Sorry about this, we should have made this more clear. The new privacy mode is needed because we have to store some state to enable running agents in the cloud. …

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 ag…

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://…

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…

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.

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

> 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.

(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 ca…

> 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 …

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

Hi. I'm an engineer at Cursor. > By prioritizing the vibe coding use case, Cursor made itself unusable for full-time SWEs. This has actually been the opposite direction we're build…