[dalemhurley]

When I started coding with AI I would copy / paste code into GPT-3.5 and ask it to update the code, it was a massive productivity boost, minor changes, fully reviewed. Then VSCode allowed tabbing, it was okayish, but I had my finger on the pulse and knew exactly what was changed and had an opinion on the suggestions. Then cursor allowed you to see and approve changes, after a few changes it started making bigger changes but had an review and approve process, things were starting to feel more magic and required more discipline to be on top of changes. Then YOLO mode hit and you could make massive changes, slowly it became easier and easier to just let the AI build code and you just guide it.

The issue is people mix up complexity, novelty, repeatability and scale.

Well documented complex problems can easily be solved by LLMs.

Doing the same thing over and over again is easy for an LLM.

Novelty and scale is very hard for an LLM.

Even small novel problems confuse LLMs.

When you start a new code base the LLM smashes through the boilerplate work. Then when it gets to scale it struggles with context rot plus novelty.