[selvan]

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?.

[ezyang]

The happy path way of getting code out of Codex is a PR. This is emphatically not true for Cursor.

[cap11235]

Feels like a sort of pollution.

[falcor84]

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?

[cap11235]

The hundreds of thousands of commits?

[falcor84]

Commits are pollution? Are you concerned that we'll run out of SHA-1 digests?

[rahimnathwani]

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.

[cap11235]

At least you know that Codex knows how to advertise itself, if nothing else.

[SkyPuncher]

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.