Dev says Claude Code harness outclassed by Zed and Cursor, forced to switch to GLM
dipankarsarkar · x · 2026-11-13
Developer dipankarsarkar complains that Claude Code's harness is no longer best in class — Zed and Cursor are far better, and despite generous limits, sub-agent handling and goal setup/autonomy are broken for real work. He finds it too rigid, repeatedly refusing cybersec tasks, forcing him to use GLM for "non-security" work.
Related event: Dev Claims Codex Harness Falls Behind Cursor and Zed(2 posts)→
More from coding & agent
- OpenAI launches ChatGPT Wallet, letting its agents complete purchases with Face ID approval — Scobleizer · 2026-11-14
- DocETL: an open-source Python library for agentic document ETL and AI data processing — mdancho84 · 2026-11-14
- Harness Engineering and Graph Engineering: two practices for reliable AI agents — Pavan_Belagatti · 2026-11-14
- Dev observes Fable 5.2 is making design decisions closer to his own than Opus 5.5 — adonis_singh · 2026-11-14
- CodeRabbit launches AI security reviews with deep scans and auto-fix PRs — PrajwalTomar_ · 2026-11-14
- Solo sci-fi filmmaker shares MiniMax H3 workflow for fixing scale drift of small props — BekesHarcos · 2026-11-14