Comment by simonw
3 days ago
The blog post had just a couple of paragraphs about the browser project, all of them accurate: https://cursor.com/blog/scaling-agents#running-for-weeks
> To test this system, we pointed it at an ambitious goal: building a web browser from scratch. The agents ran for close to a week, writing over 1 million lines of code across 1,000 files. You can explore the source code on GitHub.
> Despite the codebase size, new agents can still understand it and make meaningful progress. Hundreds of workers run concurrently, pushing to the same branch with minimal conflicts.
The commits that knocked the project into shape so other people could build the code were handled by agents as well.
I really don't think there's a notable scandal here.
I don't think there is a "scandal" here neither, companies lie and exaggerate all the time and it's becoming normalized. With that said, I think it's important to record when it happens and exactly how it happens, because not only does it help people in the future to know what to look out for, it also serves as a historical record to refer to when you start to see repeating patterns.
Agree to disagree about "all of them accurate", I've already made my case elsewhere and doesn't really help anyone to re-iterate here what's public already.
What's not true in the two paragraphs I quoted there? I'm afraid I think I need that re-iterated!
Is this just about the usage of the term "from scratch"?