

Not only that. LLMs have serious flaws like are much more costly than hand written code, are much more prone to errors, cant be reviewed or audited, and rarely employs the most efficient architectures. On top of that, execs think the memory is absolute and dont realize the more context you feed it, the more it has to guess.
LLM-only code is going to be terrible.

In my opinion, respectfully disagreed. So many professional engineers i work with or hire now forget how to code. We now allow LLMs but you must read every single line and be able to audit and explain your stack as if you read every line. And we don’t allow them for anything larger than simple functions. They are attrociously inefficient. Yet so many execs and devs think they are super intelligent. Hence why we need to call out vibe coding.