Grok Bot and Muse too dumb for business agents, says engineer comparing Claude Code
jdjohnson · x · 2026-09-28
JD Johnson says the models behind Grok Bot and Muse fail quickly when accuracy, completeness, and instruction-following are required. Cited user reports: Muse repeatedly asking for credentials it already has, forgetting recent deploy changes, ignoring 'tunnels don't work', and getting lazier. He argues Claude Code or Codex setups show a massive quality gap, and expects OpenAI and Anthropic to nail the format first.
Related event: Developer finds Grok Bot and Muse fall short of commercial agent standards(2 posts)→
More from coding & agent
- Computer use agents are suddenly making hordes of previously unusable apps usable — aronchick · 2026-09-28
- VelaTerm: open-source native app unifying coding agent sessions and split terminals — george-lin · 2026-09-28
- The Vanishing Apprentice: How AI Is Reshaping the Junior Developer Role — ArtificialOther · 2026-09-28
- Higgsfield ships 11 production skills that leave Claude with editable project files — xiaohu · 2026-09-28
- AI-generated 7-minute SQLite repo explainer stuns with coherent code walkthrough — deedydas · 2026-09-28
- Is Agentic scores how AI-agent-ready your website is, via a single npx command — seanwbren · 2026-09-28