Opus 5.5's three changes: run long tasks autonomously, skip 'think harder'
xiaohu · x · 2026-09-23
Opus 5.5 changes: it sustains multi-step long tasks better, decides its own thinking budget per reply (no more 'think carefully' prompts), and reports what it did and what needs you. Anthropic suggests: hand over the whole task with a clear finish line and stop conditions in one message, drop thinking-nudge prompts, and check blockers first when long tasks end.
Related event: Opus 5.5 guide: hand off whole tasks, intervene less(3 posts)→
More from coding & agent
- Engineer's verdict: AI eats people, not SWE jobs — edge-case thinkers win — kmeanskaran · 2026-09-23
- What would an ideal plugin editing environment inside ChatGPT/Codex look like? — Former_Worldliness70 · 2026-09-23
- boxd_sh praised as a major unlock for AI agents needing persistent computers — tobowers · 2026-09-23
- Open-source AI intraday trading bot ranks Nifty 50 every 15s and trades via Zerodha Kite — IndraVahan · 2026-09-23
- Debugging agent planners: which state do you actually save to reproduce a bad plan? — fishyguy3123 · 2026-09-23
- Yoav Goldberg: some tasks just need deterministic rules — agents can write them — yoavgo · 2026-09-23