Writer uses generate-critique-rewrite loop to fix AI errors instead of forbidding them
ivan_bezdomny · x · 2026-10-04
The author describes his approach to AI-assisted news writing: instead of telling the model not to make mistakes, he has it draft first, then run a critique-and-rewrite pass to correct errors.
His broader point: models carry priors and don't truly understand the physical world, even if they can "build 3D games." He doubts you can fix this one-shot, and plans to experiment with teaching models out of those priors, though fine-tuning might be needed.
Related event: Developer finds Opus repeats the same mistakes despite explicit prompts(5 posts)→
More from coding & agent
- Drex Router cuts small-game build cost to $1.26 vs $13.44 on Claude Opus alone — testingcatalog · 2026-11-20
- User teaches AI companion to ignore "drop it" said to his dog, then fixes the over-pause — manosaie · 2026-11-20
- NVIDIA Dynamo cuts RL rollout bottlenecks with KV-aware routing and delta weight updates — NVIDIAAI · 2026-11-20
- LangChain Academy Answers: Can a Better Model Fix a Broken Agent? — LangChain · 2026-11-20
- Agents pull AI compute back to the CPU: AWS, Google, Microsoft, NVIDIA all build on Arm — kimmonismus · 2026-11-20
- Coding agent index shows max effort costs 6x for fewer points; Gemini 4 Neon wins on value — Arindam_1729 · 2026-11-20