@cursor_ai profile picture
Cursor @cursor_ai

Coding agent for building ambitious software

Joined August 2023
  • Posts 486
  • Following 37
  • Followers 425,171
238 Photos and videos
Pinned Post
Cursor
 @cursor_ai
Apr 2
We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
1:30
782
972
10,047
2,818,879
See how Claude Fable 5 compares across every model: cursor.com/evals

Cursor · CursorBench

Compare CursorBench 3.1 results across the models Cursor evaluates.

cursor.com
22
15
203
42,807
Claude Fable 5 is available again in Cursor. It leads all models on CursorBench, but is the most expensive per task.
159
239
5,644
442,234
See our full model rankings: cursor.com/evals
15
3
95
47,744
Claude Sonnet 5 is now available in Cursor. On CursorBench, it's a meaningful step up from Sonnet 4.6: 57% vs. 49%.
206
211
4,160
1,127,262
Download Cursor for iOS on the App Store: apps.apple.com/app/cursor/id…
35
23
429
106,315
Stay in the loop with Live Activities, and get notified when an agent finishes or needs your input. Review demos and diffs before merging PRs from your phone. cursor.com/blog/ios-mobile-a…

Build from anywhere with Cursor for iOS · Cursor

Cursor is available as a native iOS app on your phone, now in public beta.

cursor.com
41
33
711
151,910
Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the app now through July 5.
1:14
961
1,146
13,067
6,354,311
More on how we're constraining eval environments so that scores better reflect model intelligence: cursor.com/blog/reward-hacki…

Reward hacking is swamping model intelligence gains · Cursor

On SWE-bench Pro, 63% of successful Opus 4.8 Max resolutions retrieved the fix rather than derived it. Stricter eval harnesses show how benchmark scores can conflate coding ability with answer...

cursor.com
17
14
302
60,652
We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a stricter harness, eval scores drop significantly.
170
300
4,715
667,952
More on how Notion built it with the Cursor SDK: cursor.com/blog/notion

How Notion used the Cursor SDK to embed coding agents · Cursor

You can now delegate tasks to Cursor directly from Notion. Notion built the integration in weeks using the Cursor SDK.

cursor.com
8
7
106
24,067
You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @​Cursor on any spec or assign it a task to open a PR your whole team can review.
0:37
113
154
2,478
308,473
You can also now use team marketplaces with GitLab, Bitbucket, and Azure DevOps in addition to local repos. cursor.com/changelog/customi…

Customize Cursor · Cursor

cursor.com
4
3
88
20,588
Plugins can now include prebuilt canvases. Use the Atlassian canvas to see a real-time view of all your issues, projects, and documents.
0:16
6
11
170
30,183
Cursor now shows you a leaderboard of the most popular plugins, skills, and MCPs across your team. Add any to your setup with one click from the new Customize page.
0:25
91
100
1,836
200,189
youtube.com/watch?v=fWa7uxyh…

Opening Keynote, Michael Truell | Compile 26

At this opening keynote of Cursor's inaugural Compile conference, c...

youtube.com
1
15
160
59,017
Three announcements from our keynote at Compile, including how we're training a new model with SpaceX.
27:01
248
896
6,992
1,259,417
We've also added GitHub triggers for issues, reviews, and workflow runs, plus computer use for cloud agents. See the full update here: cursor.com/changelog/06-18-2…

Improvements to Cursor Automations · Cursor

cursor.com
6
5
133
40,290
Cursor Automations now support an emoji trigger in Slack. React to any message to kick off a run.
0:36
9
5
232
34,566
Introducing /automate, a skill for agents to set up automations for you. Describe your task in plain language. Cursor configures the triggers, instructions, and tools.
0:25
128
269
3,343
264,457
Learn more: cursor.com/changelog/cloud-i…

Cloud Environment Setup and Cloud Subagents in Agents Window · Cursor

cursor.com
4
14
64
23,144
Load more