Grok Bot and Muse models 'too dumb' for serious business agents, says developer

jdjohnson · x · 2026-09-28

Developer jdjohnson argues the models behind Grok Bot and Muse are currently too weak to serve as general-purpose business agents: impressive at first, but they quickly fail when accuracy, completeness, and instruction-following matter. Setting up a similar workflow in Claude Code or Codex exposes a massive quality gap, he says, adding that OpenAI and Anthropic will likely figure out this new agent format before competitors.

Related event: Developer finds Grok Bot and Muse fall short of commercial agent standards(2 posts)→

Original post →

More from coding & agent

coding & agent channel →