> If that was the case, code completion and templating would have been a revolutionary, world changing development in the field.

And yet this is "AI is world changing, look at how fast it can change code!"

> So while you still try to navigate through files, others already have features out.

Your argument is "it can also read code faster too" - but it doesn't have the same tacit knowledge within the codebase. Documentation and comments can be wrong sometimes. Names are poorly chosen

That's the thing about reviews: the implementor doesn't know what's needed for the feature, but the reviewer now needs to. The latter can't trust the former anymore.

/Explain is constantly wrong. /Plan is constantly over engineered. /Tests are constantly fragile

The only benefit AI has produced to existing codebase is now people care a lot more about getting documentation right and adding little snippet/how-tos called "skills" or whatever.