alt Hacker NewsWhy is this article on top of HN? this is nothing breaking/new/interesting/astonishing..
The principles are super basic to get the first time you build an agent.
The real problem is to get reliability. If you have reliability and clear defined input and output you can easily go parallel.
THis seems like a bad 5th class homework
Replies
ramchip • yesterday at 11:30 PM
Personally I found the article informative and well-written. I had been wondering for a while why Claude Code didn't more aggressively use sub-agents to split work, and it wasn't obvious to me (I don't build agents for a living).
clbrmbr • yesterday at 11:29 PM
Perhaps because author is perhaps the most prominent agent builder outside of the big labs.
➕ show 1 reply
It doesn’t feel like news, yeah.
I would emphasize, though, that getting clearly defined input _that remains stable_ is hard. Often something is discovered during implementation of a task that informs changes in other task definitions. A parallel system has to deal with this or the results of the parallel tasks diverge.