Two 'fresh eye review' prompts catch AI coding mistakes after generation
doodlestein · x · 2026-11-10
The author finds Fable 5.2 remarkably smart but still prone to dumb mistakes, and shares his classic 'fresh eye review' prompt routine: (1) ask the model to re-read all newly written and modified code 'with fresh eyes,' hunting for obvious bugs and fixing them; (2) run a second, super-thorough pass for blunders, oversights, and omissions. The idea: make the model self-review as an independent reader after generation — two iterations catch errors a single pass misses.
More from coding & agent
- Developer dedicates a Mac mini as a home for his AI agents — ow · 2026-11-10
- Hyo adds Agent Dock to Obsidian: pin and monitor all your AI chats in one sidebar — evielync · 2026-11-10
- GPT 6.1 agent designs a cascadable broadband half-adder in a 23-minute run — CatAstro_Piyush · 2026-11-10
- Claude Code's PM #2 shares how to do devtools PM in the AI era — EricBuess · 2026-11-10
- Dev demos AI that edits documents live while you think out loud — jungofthewon · 2026-11-10
- Revolut cut its AI coding bill by 90%: 256K context enough, cache 90% of tokens — alvelda · 2026-11-10