As someone who's both an IC and leads other developers I disagree with the explanation. As a technical lead, with people I can much better predict the quality of the outcome than with LLMs, and the "failure modes" are much more manageable. As a programmer, I am actually more impressed with AI agents but in an informed and qualified way. Their debugging ability wows me; their coding ability disappoints and frustrates me.
I think that the simple explanation for why executives are so hyped about AI is simply that they're not familiar with its severe current limitations. For example, Garry Tan seems to really believe he's generating 10KLOC of working code per day; if he'd been a working developer he would have known he isn't.
I think that the simple explanation for why executives are so hyped about AI is simply that they're not familiar with its severe current limitations. For example, Garry Tan seems to really believe he's generating 10KLOC of working code per day; if he'd been a working developer he would have known he isn't.