Opus 5.5 hands-on: fast, but it rewrites your code to fit its own ideas
ssh4net · x · 2026-09-30
User ssh4net shares hands-on impressions of Anthropic's new Opus 5.5: the model is noticeably fast and follows a defined set of coding skills well, but tends to write code the way it wants rather than what the user and technical specs demand — sometimes changing the core idea mid-project. Post-hoc code review and adding stricter rules to specs only partially helps.
Related event: Opus 5.5 Is Fast but Often Ignores User Specs, Early Tests Show(2 posts)→
More from coding & agent
- AI.CLASSIFY coming to Quail: rethink OLAP-style AI operations on data — sh_reya · 2026-09-30
- Ant Group's Marathoner Trains Agents to Work 10+ Hours With 1000+ Tool Calls — antgroup · 2026-09-30
- Supply Chain Agent Lesson: Memory Knows the Rules, Code Enforces Them — Chemical_Pickle5979 · 2026-09-30
- Artificial Analysis open-sources agent inference benchmark, first results for DGX Spark, RTX 5090, M5 Pro — ArtificialAnlys · 2026-09-30
- Feed Your Agents Markdown: How a Good API Turned cf CLI Into an Unexpected Agent Tool — irvinebroque · 2026-09-30
- 14% of AI-Written Tests Were Useless: The Checker Rewarded Typing Words, So Agents Typed Them — Input-X · 2026-09-30