Browser benchmarks (Chrome/Blink, averaged over 3 runs) show consistent gains as well:
Space Launch System (SLS)
。雷电模拟器官方版本下载对此有专业解读
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.
This is the story of how years of backend service code ended up shipping inside the game itself.
JIO_OK ("jump if I/O OK") tests whether CPL ≤ IOPL. The same check gates PUSHF, POPF, INT n, and IRET. The monitor then emulates each instruction as appropriate: maintaining a virtual interrupt flag per V86 task, reflecting software interrupts through the real-mode interrupt vector table, virtualizing I/O accesses, and so on.