Make Claude and ChatGPT cross-review each other; humans shouldn't be the courier
sujingshen · x · 2026-10-07
The author shares a multi-model workflow: let one model write (HTML/doc/ppt) while the other critiques, with the human just relaying between them. The pain point is that no product supports this natively—the ideal would be a tool that runs both models automatically and surfaces their disagreements for the user, instead of making humans do the shuttling by hand.
More from coding & agent
- OpenAI deprecates legacy user API keys, migration deadline Oct 22 — ThePeterMick · 2026-10-07
- YourHand: open-source AI agent that controls multiple Windows PCs from one chat — arch_ahmedzaki · 2026-10-07
- One-line AGENTS.md tweak: tell your coding agent you're a tired engineer — cem2ran · 2026-10-07
- mitsuhiko: the bash tool makes codemode surprisingly hard to explain — mitsuhiko · 2026-10-07
- Agent harness replicates Minecraft builds: maps, places blocks and generates its own assets — Promptmethus · 2026-10-07
- Developer has Codex build a Solarman solar-monitoring macOS app in 3 minutes — Dimillian · 2026-10-07