Ask HN:有人在尝试使用 LLM 进行编程的不同方法吗?

7 分•作者: yehiaabdelm•3 个月前
我对在使用大型语言模型进行编程方面感觉有些停滞不前,这让我有点恼火。 我使用 Claude Code 和 Codex,但无法像手写代码时那样进入心流状态。 这对我来说有点讽刺,因为人工智能本应是“思想的自行车”,但现在感觉就像一辆每隔几分钟就会突然刹车的自行车。我需要停下来,等待,审查,然后再次提示。 有人在探索与我们今天所拥有的提示-响应循环根本不同的方法吗? 我实际上认为“标签模型”比提示-响应模型方向上更好。 我很想了解任何相关的初创公司、个人实验等。
查看原文
I&#x27;m a bit annoyed by the feeling that we&#x27;re kind of stuck when it comes to using LLMs for programming.<p>I use Claude Code and Codex, but I haven&#x27;t been able to enter flow state like I can when I hand write code.<p>This is kind of ironic to me since AI should be a bicycle for the mind, but right now it feels like a bicycle that just brakes abruptly every couple minutes. I stop, wait, review, prompt again.<p>Is there anyone exploring something fundamentally different than the prompt response loop we have today?<p>I actually think the idea of a tab model is directionally better than prompt response.<p>Would love to hear about any startups, personal experiments, etc.