The big finding: Claude Code builds, not buys. Custom/DIY is the most common single label extracted, appearing in 12 of 20 categories (though it spans categories while individual tools are category-specific). When asked “add feature flags,” it builds a config system with env vars and percentage-based rollout instead of recommending LaunchDarkly. When asked “add auth” in Python, it writes JWT + bcrypt from scratch. When it does pick a tool, it picks decisively: GitHub Actions 94%, Stripe 91%, shadcn/ui 90%.
First FT: the day’s biggest stories，更多细节参见safew官方下载
Text-to-speech feature reads work out loud，这一点在WPS下载最新地址中也有详细论述
Что думаешь? Оцени!
Identify who spoke when — detects up to 4 speakers with per-frame activity probabilities: