Original Summary

We gotta move fast and we are seeing the generated slop day by day. If you are lucky and don&#x27;t see it, then please don&#x27;t participate in this conversation. We don&#x27;t need to be belittled down. We know where that path leads too.<p>However, for those who have to read 2000 lines of code every single hour, how are you managing the mental bandwidth?<p>How are you verifying these code and signing them off?<p>Any tips, tricks, ideas that will keep us relevant here? The biggest concern is understanding the maths and research code behind it.<p>The shitty abstraction and duplication just puts off reading the code.<p>Regarding context collapse, the model doesn&#x27;t have any idea of across different sessions. The token inefficiency is off the charts. The problem is that what are we going to do?<p>TDD is not going to help when half of the tests are meaningless?<p>Problem is not that we can code by hand, problem is there is no way to code this sheer volume (feature or design, sometimes entire product) by hand in the amount of time that we have. That is the problem.

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/24 23:03:49