[xt00]

Totally agree — if AI tools are already or nearly at the point where you can say “write a program to do X” and it does it, that’s like telling people they need to learn skills to order something at McDonald’s. The goal is for the barrier to entry to be basically zero. Oh sure today there are things like “I made a claude.md file that does this and I wrote a really clever prompt!!” But the goal is for that work to be deleted as well — where is the magic skill that is / will be needed?

[Zigurd]

I use coding agents every day for non-trivial projects. But I can definitely say that a prompt of the form "Write a program that does X" will earn you a git rollback of a mess, unless what you want has been done a bazillion times before.

Peak efficiency in using coding agents is a weird balancing act at this point in the development of coding agents: being too incremental and detailed is inefficient, but if you let it rip on a task with multiple sub tasks you have to be ready for the coding agent to get utterly lost while providing you with only hints at what made it to lose its way. It's like an inexperienced intern with a high opinion of its competency.

LLMs trained for coding are most productive when pushed to their limits, but that's where they start to fall down.