News for hackers. Stuff that matters.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by selvan on Sunday June 08, 2025 @11:27PM (#44221201)
Total PRs between Codex vs Cursor is 208K vs 705, this is an enormous difference in absolute PRs. Since cursor is very popular, how does their PRs is not even 1% of codex PRs?.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by rahimnathwani on Sunday June 08, 2025 @11:43PM (#44221260)
I didn't even realize Cursor could make PRs. I thought most people would create PRs themselves once they were happy with a series of commits.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by cap11235 on Monday June 09, 2025 @04:02AM (#44222342)
At least you know that Codex knows how to advertise itself, if nothing else.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by ezyang on Sunday June 08, 2025 @11:38PM (#44221236)
The happy path way of getting code out of Codex is a PR. This is emphatically not true for Cursor.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by cap11235 on Sunday June 08, 2025 @11:55PM (#44221306)
Feels like a sort of pollution.
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by falcor84 on Monday June 09, 2025 @06:02AM (#44222841)
Why? That is its intent - unlike an IDE, it is intended to work autonomously and only get back to you after it has prepared the full changeset - which at that point you'd review via a PR. Where's the pollution in that?
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by cap11235 on Monday June 09, 2025 @07:00AM (#44223166)
The hundreds of thousands of commits?
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by falcor84 on Monday June 09, 2025 @07:27AM (#44223356)
Commits are pollution? Are you concerned that we'll run out of SHA-1 digests?
Re:Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Perfor... by SkyPuncher on Monday June 09, 2025 @10:45AM (#44225028)
This is only comparing _agents_, which is going to exclude pretty much all Cursor usage for two reasons:

* Cursor agents where just introduced in Beta and have privacy limitations that prevent their usage as many organizations.

* Cursor is still focused on hands-on-keyboard agentic flows, which aren't included in these counts.