ChatGPT's automations are its weakest part, argues dev who prefers Claude monitoring and Amp triggers
carlosdponx · x · 2026-09-09
The author argues automations are ChatGPT's weakest feature, with too little iteration. Claude's "monitoring" is far more useful for coding, and @AmpCode goes further by supporting not just timed automations but arbitrary agent-defined triggers (webhooks, etc.).
Key criticism: ChatGPT's automations are defined at a global level and only target (pinned) threads — the wrong layer of abstraction entirely.
More from coding & agent
- New Urbit library %opal turns every agent state face into a scry endpoint with one line — BLUECOW009 · 2026-09-09
- OpenClaw 2026.9.3 ships: 1,844 PRs, cloud repo work, live browser automation — steipete · 2026-09-09
- Stripe Exec: The Easiest Way to Get Agent-Ready Is Agent-Friendly Checkout — jeff_weinstein · 2026-09-09
- How Cursor's Shipping Velocity Broke GitHub's Moat — and No One Owns SOTA Now — pzakin · 2026-09-09
- Ladybird Browser Ships Big Month: Twitch Playback, JS Debugging, Rust Migration — unixterminal · 2026-09-09
- GitHub's HydraFusion in Copilot CLI Auto-Routes Tasks Across Draft-Critique-Revise — unixterminal · 2026-09-09