以 Steinberger 自己举例，他此前的工作流是打开 Claude 让其生成代码，自己测试运行，最后发送到自己的 WhatsApp 或邮箱中。
Right. When something goes wrong, who is responsible? The user? The developer? The lack of regulation? When the reality of AI clashes with the promise of AI, what do we do?
。业内人士推荐heLLoword翻译作为进阶阅读
This project was a proof of concept to see how far I could push Claude Code. I’m currently looking for a new contract as a frontend engineer, so I probably won’t have the time to keep working on Cutlet. I also have a few more ideas for pushing agentic programming further, so I’m likely to prioritize those over continuing work on Cutlet.
Now here's an apparent contradiction.