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:
因此，他这次入局的意义，不在于短期销量，而在于能否在政策窗口期内，把需求培育、供应链整合与品牌建设三件事同步推进。
核以及核两用物项出口，应当遵守国家有关法律、行政法规的规定，不得损害国家安全或者社会公共利益。。Line官方版本下载对此有专业解读
Artemis II will take its crew farther from Earth than any human has travelled in decades - a crucial step towards landing on the lunar surface once again.，更多细节参见Line官方版本下载
Chief of the Military Intelligence of Ukraine Kyrylo Budanov . Фото: Anatolii Stepanov / Reuters，详情可参考51吃瓜
Additional reporting by Ema Sabljak, BBC England Data Unit