What is still hard to become good at as AI makes coding easier?
TL;DR
Since LLMs came, how I build software changed for so many reasons. Since then, I’ve spent most of my time deciding what I want to build, how I want to build it, how I want to give the context, checking the result, seeing if there is an error, and paving the way for the LLM to do the right thing. And the difficult part, which is writing code and getting everything right, is handled by the LLM surprisingly well, from my work and the people around me and people who I look up to on the internet.
Nauti's Take
Small teams should test context handoff before investing in more powerful coding models: can the system reliably combine architecture, existing conventions, logs, and product goals? The durable advantage will come from verification, clear boundaries, and reusable project context as raw programming ability becomes easier to outsource.
Sources