unofficial account crossposting from Twitter - run by
@danielmorrisey.com
x.com/cursor_ai
Our benchmarks show it as a notable improvement over Sonnet 4.5 on longer tasks, but below Opus 4.6 for intelligence.
Our benchmarks show it as a notable improvement over Sonnet 4.5 on longer tasks, but below Opus 4.6 for intelligence.
With our new harness, agents can complete much larger tasks.
http://cursor.com/blog/long-running-agents
With our new harness, agents can complete much larger tasks.
http://cursor.com/blog/long-running-agents
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.
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.
We’ve found it to strike a strong balance between intelligence and speed.
We’ve found it to strike a strong balance between intelligence and speed.
It's noticeably faster than 5.2 and is now the preferred model for many of our engineers.
It's noticeably faster than 5.2 and is now the preferred model for many of our engineers.
It's 2.5x as fast in research preview.
It's 2.5x as fast in research preview.
It's highly effective at long-running tasks and reviewing code.
It's highly effective at long-running tasks and reviewing code.
In a recent week-long run, our system peaked at over 1,000 commits per hour across hundreds of agents.
We're sharing our findings and an early research preview inside Cursor.
In a recent week-long run, our system peaked at over 1,000 commits per hour across hundreds of agents.
We're sharing our findings and an early research preview inside Cursor.
https://agent-trace.dev
https://agent-trace.dev
For very large codebases, Cursor's indexing process is now several orders of magnitude faster.
http://cursor.com/blog/secure-codebase-indexing
For very large codebases, Cursor's indexing process is now several orders of magnitude faster.
http://cursor.com/blog/secure-codebase-indexing