I don't think it's denial, because it has simply been true that even as many tasks have been automated away, there have been multiplicatively more tasks that haven't yet. Nobody really knows whether we should be optimistic or pessimistic about that trend continuing, but I think we should be more aware that it isn't fundamentally different than similar trends in other types of work in the past.
> it has simply been true that even as many tasks have been automated away, there have been multiplicatively more tasks that haven't yet.
In part this is the denial I talked about. Many of the multiplicatively tasks we have are the result of not finding how to solve obvious problems with pragmatic solutions. Let me explain:
Everytime we came up with new programming environments and languages we repeat the same cycles. It is very rare to have a real breakthrough. For example, once NodeJS become popular we are happy when someone introduce libraries that already existed in another language instead of automating the production of these libraries. All this work can be reduced to some software to generate stuff for multiple languages. Surely you can't apply this for different paradigms but there are few programming paradigms being used in production.
If you follow this approach you will only need a proportion of the people that is working now.
Another example: big corporations. I don't talk about Google or Facebook, I talk about the typical big corporation. If you walk around you can find that replacing a lot of IT employees is relatively easy with good organization. In a way we are protecting our own work not thinking very hard about how to replace people.
