Codex and Grok Bot share the same flaw: making users do the organizing
jesselyu · x · 2026-09-15
cellier argues Codex (task-centered) and Grok Bot/Muse (bot-centered) share one fundamental error: both offload AI organization onto users — either by mimicking human job roles ('which bot do I ask?') or traditional software structure ('which task/chat/project?'). Since AI isn't human, users should express intent in one persistent AI relationship and let the AI handle context and organization itself. jesselyu endorsed the take.
More from coding & agent
- Snapcompact renders context as pixel-font bitmaps, cutting LLM input costs ~2x — brandon_galang · 2026-09-15
- Benzi lets you chat with any public GitHub repo, now shipped as a VS Code extension — DonkeyTheKing · 2026-09-15
- Ant Ling, Hugging Face and NVIDIA to host hands-on local AI assistant session on Sept 17 — heyneighbor · 2026-09-15
- Dev turns 2 weeks of Obsidian plugin experience into open-source Skill that lets Codex build and ship plugins — vista8 · 2026-09-15
- Tencent open-sources WeKnora, an enterprise RAG knowledge platform with 23.3k GitHub stars — yangyi · 2026-09-15
- Dev open-sources Taskuary, a local control layer that gives coding agents a shared task queue — Appropriate-Path-461 · 2026-09-15