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:
Key Capabilities，更多细节参见新收录的资料
。新收录的资料是该领域的重要参考
Hurdle Word 2 hintGrumpy.
这个功能把纠偏这件事从「完成后」提前到了「执行中」，对需要多轮协作的任务来说，体验差别会比较明显。功能目前已在 chatgpt.com 和 Android 应用上线，iOS 版本即将跟进。。关于这个话题，新收录的资料提供了深入分析