Right. There IS a way to convince ai to write less code.. but it obviously spends 10x tokens, whether it’s LLMs as judge and automated review or just write 10 solutions and keep 1. Partly ai companies like it this way but partly it’s unintentional consequences that happen to work in their favor.
Training for good taste in architecture actually causes premature optimization at high effort allowance, but at the same time, it is combined with an inability to even recognize / exploit that later if it should ever become actually useful. Dial the effort down, and it skips the reasonable abstraction and nothing is dry, factoring is insane.
Goldilocks for simple stuff barely works with frontier models after they are out of their comfort zone for topic or line limits.. you kind of just have to decide whether it’s worth it anyway. In practice.. constant supervision for high quality code, or such high quality system design that the code quality is less of a down side.
alt Hacker News
Right. There IS a way to convince ai to write less code.. but it obviously spends 10x tokens, whether it’s LLMs as judge and automated review or just write 10 solutions and keep 1. Partly ai companies like it this way but partly it’s unintentional consequences that happen to work in their favor.
Training for good taste in architecture actually causes premature optimization at high effort allowance, but at the same time, it is combined with an inability to even recognize / exploit that later if it should ever become actually useful. Dial the effort down, and it skips the reasonable abstraction and nothing is dry, factoring is insane.
Goldilocks for simple stuff barely works with frontier models after they are out of their comfort zone for topic or line limits.. you kind of just have to decide whether it’s worth it anyway. In practice.. constant supervision for high quality code, or such high quality system design that the code quality is less of a down side.