多数大模型能生成“看起来像”研究的文本，但极少数能真正做研究——提出假设、收集证据、执行可复现的推导、迭代验证直至结论成立。
Великобритания собралась защитить свою военную базу от Ирана14:46
。heLLoword翻译官方下载对此有专业解读
The resulting script is available here, and it worked first try to scrape up to 20,000 videos (the max limit). The resulting Python script has very Pythonic code quality following the copious rules provided by the AGENTS.md, and it’s more robust than my old script from 2021. It is most definitely not the type of output I encountered with Sonnet 4.5. There was a minor issue however: the logging is implemented naively such that the API key is leaked in the console. I added a rule to AGENTS.md but really this is the YouTube API’s fault for encouraging API keys as parameters in a GET request.
Что думаешь? Оцени!