I agree that actual tests are also necessary, that code review is not enough by itself. As LLMs can also write tests, I think getting as close as is sane to 100% code coverage is almost the first thing people should be doing with LLM assistance (and also, "as close as is sane": make sure that it really is a question of "I thought carefully and have good reason why there's no point testing this" rather than "I'm done writing test code, I'm sure it's fine to not test this", because LLMs are just that cheap).

However, code review can spot things like "this is O(n^2) when it could be O(n•log(n))", or "you're doing a server round trip for each item instead of parallelising them" etc.

You can also ask an LLM for a code review. They're fast and cheap, and whatever the LLM catches is something you get without having to waste a coworker's time. But LLMs have blind spots, and more importantly all LLMs (being trained on roughly the same stuff in roughly the same way) have roughly the same blind spots, whereas human blind spots are less correlated and expand coverage.

And code smells are still relevant for LLMs. You do want to make sure they're e.g. using a centralised UI style system and not copy-pasting style into each widget, because duplication wastes tokens and is harder to correctly update with LLMs for much the same reason it is with humans: stuff gets missed during the process when it's copypasta.

I am personally working on formalizing the design stage as well, the core concepts being Architecture, Goal, Solution and Implementation. That would make something like the complexity of an algorithm an explicit decision in a graph. It would make constraints and dependencies explicitly formalized. You can track any code to its solution (design stage) and goals, account for everything top-down and bottom-up, and assign tests for all nodes.

Take a look here: https://github.com/horiacristescu/archlib/blob/main/examples... (but it's still WIP, I am not there yet)