I’m well aware, thank you, have been coding for 40+ years (including 6502 and 68000 assembly), masters in computer science, have built healthcare software where bugs can lead to death. But with LLMs enabling us to generate source code faster, our review process is becoming an increasingly larger bottleneck for productivity. We need to start thinking how we can scale this process.
It's as much bottleneck for productivity as cars being made of metal are bottleneck for speed. Sure, you can make a paper car. It probably would be faster. Until you collide with something and then you discover why the metal frame was a good idea. If you generate code that you can not verify or test, sure, it's faster. Until something goes wrong.
That is why formula 1 race cars are mostly carbon fiber, including the frame. They identified the bottleneck, and replaced it with a better solution...
Better solution for a race car, driven on specialized tracks, by highly seasoned professional, who is paid enormous money, in compensation for the grave risks he is taking. It's not a better solution for everyday car driven by everyday person. Most race cars aren't even street legal, and getting arrested for driving one on the street would be the best outcome. Getting seriously hurt would be most likely.
