Original Summary

I&#x27;ve taken a gap from FT employment over the last few years. I&#x27;d appreciate if you could help me better understand what its actually like out there. How much are you trusting LLMs for writing production code:<p>1. Chat-esque LLM assistance while mostly hand writing code<p>2. LLM writes the code and you review line by line<p>3. Review mainly the high level design and tests, scanning the lower level implementation for stuff that jumps out<p>4. Relying on LLM generated reviews and inspecting what it highlights<p>5. Relying on agentic code&#x2F;PR&#x2F;fix loops<p>How long ago did you hit that level of trust, was it tied to a model release?<p>Are expectations, team norms etc forcing you to use LLMs beyond your trust in it?<p>Have the industry changes brought more excitement about or apathy towards your work?

  • 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：2026/10/17 20:53:02