Claude Opus 5 may narrate mid-response fixes, breaking structured outputs
heypearlai · x · 2026-07-29
Tell Opus 5 to stop narrating its corrections
If Opus 5’s output is going into a parser or UI, the thread warns that it narrates its own corrections more often than 4.8 did. Mid-response, it may explain that an earlier approach was wrong and that it has switched plans.
That is acceptable in chat, but it is problematic for structured fields. The recommended instruction is to ask for only the final answer and keep revised reasoning out of the response.
Related event: Prompting Tips and Pitfalls for Claude Opus 5(4 posts)→
More from coding & agent
- Building a portable context vault in Notion so every AI agent knows you from day one — ivanhzhao · 2026-10-16
- Lovable apps can now talk to customers on WhatsApp with inbox, reminders and templates — AlexandrePesant · 2026-10-16
- Deep Research API showdown: OpenAI, Perplexity, Parallel, Tavily, Gemini, Valyu compared — bar_raiser333 · 2026-10-16
- Geoffrey Huntley open-sources Overalls, a self-hosted AI developer platform under MIT — kieranklaassen · 2026-10-16
- Dev shows 199.7bn tokens over 200 days on OpenAI Codex, peak 8.6bn/day — Dimillian · 2026-10-16
- Ask Claude to open its changes in nvim and scroll to the exact line for review — max__drake · 2026-10-16