But you can still solve problems and write code by hand on your own for your hobby projects. You do not need to solve problems only in paid job. However I think with LLMs/AI you can go further and do more difficult problems. Of course somebody can create whole app faster and from scratch etc. but it does not mean that person will understand everything. But what does this person really need to know? Implementation details such as every piece of code (ihmo not possible), selected framework details, business logic code, high overview of architecture? But why do we treat programming language backend and "under the hood code" as not necessary artifacts? "Because it is complex and possible for single human". Yes and with LLMs generated code we go further. Whole apps will be artifacts, pieces of bigger and more complex systems. I guess it will be like this but I am not sure, we will see.