You spend a few minutes generating a spec, then agents go off and do their coding, often lasting 10-30 minutes, including running and fixing lints, adding and running tests, ...
Then you come back and review.
But you had 10 of these running at the same time!
You become a manager of AI agents.
For many, this will be a shitty way to spend their time.... But it is very likely the future of this profession.
You want to do that, but Ill bet money you arent doing it.
Thats the problem: this is speculative; maybe it scales sometimes, but mostly people do not work on ten things at once.
“Fix the landing page”
“I’ll make you ten new ones!”
“No. Calm down. Fix this one, and do it now, not when youre finished playing with your prompts”
There are legitimate times when complex pieces of work decompose into parallel tasks, but its the exception not the norm.
Most complex work has linked dependencies that need to be done in order.
Remember the mythical man month? Anyone? Anyone???!!??
You can't just add “more parallel” to get things done faster.
Codex / Jules etc make this pretty easy.
It's often not a sustainable pace with where the current tooling is at, though.
Especially because you still need to do manual fixes and cleanups quite often.
Mhm. Money -> to the dealer.
Anyway… watch the videos the OP has of the coding live streams. Thats the most interesting part of this post: actual real examples of people really using these tools in a way that is transferable and specifically detailed enough to copy and do yourself.
You can’t do 10 of these processes at once, because there’s 8 minutes of human administration which can’t be parallelised for every ~20min block of parallelisable work undertaken by Claude. You can have two, and intermittently three, parallel process at once under the regime described here.
That coupled with the fact that you have to meticulously review every single thing the AI does is going to obliterate any perceived gains you get from going through all the trouble to set this up. And on top of that it's going to be expensive as fuck quick on a non trivial code base.
And before someone says "well you don't have to be that thorough with reviews", in a professional settings absolutely you do. Every single AI policy in every single company out there makes the employee using the tool solely responsible for the output of the AI. Maybe you can speed run when you're fucking around on your own, but you would have to be a total moron to risk your job by not being thorough. And the more mission critical the software the more thorough you have to be.
At the end of the day a human with some degree of expertise is the bottleneck. And we are decades away from these things being able to replace a human.
Joke's on you (and me? and I guess on us as a profession?).
This can all be done autonomously without user interaction. Now many bugs can be few lines of code and might be relatively easy to review. Some of these bug fixes may fail, may be wrong etc. but even if half of them were good, this is absolutely worth it. In my specific experience the success rate was around 70%, and the rest of the fixes were not all worthless but provided some more insight into the bug.