News for hackers. Stuff that matters.

A comment on Mark Zuckerberg tells staff that AI agents haven't progressed enough. Parent comment

Re:Mark Zuckerberg tells staff that AI agents haven't progre... by rogerrogerr on Sunday July 05, 2026 @07:51PM (#48799173)
You can have a separate LLM as a brutal enforcer of an architecture decision. Works pretty well in the right harness.
[ Parent | on HN ]
Re:Mark Zuckerberg tells staff that AI agents haven't progre... by Toutouxc on Monday July 06, 2026 @06:29AM (#48802827)
Wider architectural guidelines, yes. "How a senior developer in this company would do it" — not so much.
[ Parent | on HN ]
Re:Mark Zuckerberg tells staff that AI agents haven't progre... by rogerrogerr on Monday July 06, 2026 @10:28AM (#48805148)
That’s what code review is still for.
[ Parent | on HN ]