Comment by saghm
16 hours ago
The point is to learn how to make very large codebases that don't compile? Why do you need tests and specs if it's not going to even run, much less run correctly?
16 hours ago
The point is to learn how to make very large codebases that don't compile? Why do you need tests and specs if it's not going to even run, much less run correctly?
As discussed elsewhere, it is apparently possible to compile and run this particular project. It seems that whatever process they followed allows commits to break the build pretty often.
Nevertheless, IMHO what’s interesting about this is not the browser itself but rather that AI companies (not just Cursor) are building systems where humans can be out of the loop for days or weeks.
> As discussed elsewhere, it is apparently possible to compile and run this particular project.
After a human stepped in to fix it, yes. You can see it yourself here: https://github.com/wilsonzlin/fastrender/issues/98
> Nevertheless, IMHO what’s interesting about this is not the browser itself but rather that AI companies (not just Cursor) are building systems where humans can be out of the loop for days or weeks.
But that's not what they demonstrated here. What they demonstrated, so far, is that you can let agents write millions of lines of code, and eventually if you actually need to run it, some human need to "merge the latest snapshot" or do some other management to actually put together the system into a workable state.
Very different from what their original claims were.