与“买一个品牌”不同，这种方式更像是在现有能力边界上做延伸，风险更可控，但回报节奏也相对较慢。
Claude Code worked for 20 or 30 minutes in total, and produced a Z80 emulator that was able to pass ZEXDOC and ZEXALL, in 1200 lines of very readable and well commented C code (1800 lines with comments and blank spaces). The agent was prompted zero times during the implementation, it acted absolutely alone. It never accessed the internet, and the process it used to implement the emulator was of continuous testing, interacting with the CP/M binaries implementing the ZEXDOC and ZEXALL, writing just the CP/M syscalls needed to produce the output on the screen. Multiple times it also used the Spectrum ROM and other binaries that were available, or binaries it created from scratch to see if the emulator was working correctly. In short: the implementation was performed in a very similar way to how a human programmer would do it, and not outputting a complete implementation from scratch “uncompressing” it from the weights. Instead, different classes of instructions were implemented incrementally, and there were bugs that were fixed via integration tests, debugging sessions, dumps, printf calls, and so forth.
，推荐阅读爱思助手下载最新版本获取更多信息
Linux kernel maintainers propose a less painful process for identifying developers. See how it can make Linux code safer than ever.
当越来越多「Agent」能够被像软件一样使用，AI 对工作方式的影响，才会真正开始外溢。