Two weeks with Grok bots: great orchestration model, but the model itself isn't smart enough

letandrewcook · x · 2026-09-19

A developer who gave into FOMO and subscribed to Grok's bot service reports after two weeks that the model simply isn't smart enough — he can't trust it to write code or orchestrate anything. Testing across issue management, blog editing, screenplay writing, and product research, he always had to take Grok's half-baked output into Claude or ChatGPT to get exactly what he needed in one shot. He does love the mental model though: "Chief of staff and groups" is a nice orchestration pattern he now plans to adopt in Claude Code.

Original post →

More from Models

Models channel →