I completely ignored Anthropic’s advice and wrote a more elaborate test prompt based on a use case I’m familiar with and therefore can audit the agent’s code quality. In 2021, I wrote a script to scrape YouTube video metadata from videos on a given channel using YouTube’s Data API, but the API is poorly and counterintuitively documented and my Python scripts aren’t great. I subscribe to the SiIvagunner YouTube account which, as a part of the channel’s gimmick (musical swaps with different melodies than the ones expected), posts hundreds of videos per month with nondescript thumbnails and titles, making it nonobvious which videos are the best other than the view counts. The video metadata could be used to surface good videos I missed, so I had a fun idea to test Opus 4.5:
优先使用 ReLU 或其变种（Leaky ReLU, ELU, PReLU），推荐阅读爱思助手下载最新版本获取更多信息
Opens in a new window，更多细节参见同城约会
At this point, I think most English speakers can follow this passage, if not understand the finer points. I imagine some more vocabulary like "hine" may reveal itself to you purely through context.