>Except that reviewing has become just asking your agent what that piece of code does in english
How does this work for you?
Do you ask about specific functions ("what does this function do")? Then it sounds like more work than actually reading it.
Or do you ask about the whole PRs ("what does this PR implement")? Then how do you catch things like security vulnerabilities, bad design choices, unnecessary dependencies, wrong architecture, etc? Those are things that benefit the most from human understanding (nitpicking style was always the easy but unimportant part of code review)
How does this work for you?
Do you ask about specific functions ("what does this function do")? Then it sounds like more work than actually reading it.
Or do you ask about the whole PRs ("what does this PR implement")? Then how do you catch things like security vulnerabilities, bad design choices, unnecessary dependencies, wrong architecture, etc? Those are things that benefit the most from human understanding (nitpicking style was always the easy but unimportant part of code review)