Code might be cheaper but it's still a liability. In that regard anything that's not been properly designed and documented is going to be an even bigger issue.
My vision for a new internet is a space where we can guarantee something is coming from an human and is genuine. The second point is that we get paid for feeding our AI overlords
There's new evidences that even Sapiens "introduction" in Europe happend multiple times in the scale of thousand years with migratory waves comming from Africa/Middle East.
There's a 12h Collège de France course from Jean-Jacques Hublin that display new understandings that is really captivating. It's in French though
Sub agent also helps a lot in that regard. Have an agent do the planning, have an implementation agent do the code and have another one do the review. Clear responsabilities helps a lot.
There also blue team / red team that works.
The idea is always the same: help LLM to reason properly with less and more clear instructions.
That's the thing that bothers me here. They loaded the doc of course it will work but as your project grows you won't be able to put all your documentation in there (at least with current context handling).
Skills are still very much relevant on big and diverse projects.
I've got an AMD Ryzen 9 365 processor on my new laptop and I really like it. Huge autonomy and good performance when needed, it's comparable to the M3 version (not the Max).