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.
More from Models
- Burkov: closed LLM providers bill you for hidden thinking tokens you can never verify — burkov · 2026-09-19
- DiffusionGemma's native vision tower runs near-real-time object detection on a phone — bodonoghue85 · 2026-09-19
- Claim: DeepSeek v4.1 builds its own training tasks with generate-verify-re-audit pipelines — teortaxesTex · 2026-09-19
- A new kind of AI model from a ChatGPT inventor is thrilling developers — TechCrunch AI · 2026-09-19
- Is Jev Actually Accurate? Engineer Flags 99/1 Answer to a 60/40 Coin Question — JnBrymn · 2026-09-19
- LLM fails coin-flip probability test, says 60/40 coin is 99/1 — JnBrymn · 2026-09-19