I've taken a gap from FT employment over the last few years. I'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:1. Chat-esque LLM assistance while mostly hand writing code2. LLM writes the code and you review line by line3. Review mainly the high level design and tests, scanning the lower level implementation for stuff that jumps out4. Relying on LLM generated reviews and inspecting what it highlights5. Relying on agentic code/PR/fix loopsHow long ago did you hit that level of trust, was it tied to a model release?Are expectations, team norms etc forcing you to use LLMs beyond your trust in it?Have the industry changes brought more excitement about or apathy towards your work? Comments URL: https://news.ycombinator.com/item?id=50130686 Points: 1

Comments: 0