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
- Mitchell Hashimoto Starts New Company for AI-Era Terminal Multiplexer — jedisct1 · 2026-07-29
- Steve Yegge says only Fable has earned his trust inside Claude Code — Steve_Yegge · 2026-07-29
- Vibecoding turns one more task into a 24/7 coding-agent loop — danshipper · 2026-07-29
- Sightmap open-sources a YAML runtime memory map for AI coding agents — hwchase17 · 2026-07-29
- Developers are pointing Claude straight at the database and skipping the usual stack — EricBuess · 2026-07-29
- Claude Opus 5 still needed iterations to build a custom racing game — mattshumer_ · 2026-07-29