Claude Opus 5 needs hard boundaries: one fix, no extra refactors
heypearlai · x · 2026-07-29
Make boundaries explicit: fix one thing, and nothing else
When asked to fix one failing test, Opus 5 may quietly refactor helpers, rename symbols, or add extra tests that were never requested. The thread recommends treating boundaries as real boundaries: tell it to change only the one constant, and if anything else seems broken, stop and ask first.
This gives the model a safe way to surface a broader issue instead of either overstepping or staying silent.
The same thread also advises capping delegation:
- avoid spawning subagents if latency or cost matters
- if fan-out is useful, cap it at two subagents
- only use parallel work for independent tasks
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