Nature, Published online: 24 February 2026; doi:10.1038/d41586-026-00590-0
（本报记者赵成、吴丹、朱隽、王昊男、侯琳良、杨文明、王云娜、刘军国、李心萍、寇江泽、李林蔚、常钦、刘新吾、郑洋洋、李俊杰）
，这一点在51吃瓜中也有详细论述
政者，正也。政绩观树得正，办事情才能过得硬。
During development I encountered a caveat: Opus 4.5 can’t test or view a terminal output, especially one with unusual functional requirements. But despite being blind, it knew enough about the ratatui terminal framework to implement whatever UI changes I asked. There were a large number of UI bugs that likely were caused by Opus’s inability to create test cases, namely failures to account for scroll offsets resulting in incorrect click locations. As someone who spent 5 years as a black box Software QA Engineer who was unable to review the underlying code, this situation was my specialty. I put my QA skills to work by messing around with miditui, told Opus any errors with occasionally a screenshot, and it was able to fix them easily. I do not believe that these bugs are inherently due to LLM agents being better or worse than humans as humans are most definitely capable of making the same mistakes. Even though I myself am adept at finding the bugs and offering solutions, I don’t believe that I would inherently avoid causing similar bugs were I to code such an interactive app without AI assistance: QA brain is different from software engineering brain.