To those who have played around with LLM code generation more than me, how are they at debugging?
I'm thinking of Kernighan's Law: "Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it." If vibe coding reduces the complexity of writing code by 10x, but debugging remains just as difficult as before, then Kernighan's Law needs to be updated to say debugging is 20x as hard as vibe coding. Vibe coders have no hope of bridging that gap.
There's a lot to it. The campaign consultants who keep losing on a "don't rock the boat" strategy keep getting hired for the next campaign. Doesn't matter how many times they fail.
James Carville has made a career out of winning an election where the Dem was considered an underdog. Others have been trying to copy his style ever since, but it doesn't work.