Comment by thenanyu
19 days ago
Agents can write good code. If you don't like the way that they write code, tell them to write it differently. Do that until you think the code is good.
19 days ago
Agents can write good code. If you don't like the way that they write code, tell them to write it differently. Do that until you think the code is good.
There's an opportunity-cost here. I use agents to be more productive. As many have noted, "Good Code" doesn't rank highly compared to actually shipping a product.
The tragedy, for me, is that the bar has been lowered. What I consider to be "good enough" has gone down simply because I'm not the one writing the code itself, and feel less attachment to it, as it were.
Doesn’t the question then become “is there still an objective advantage to good code”
If the answer is yes then it’s a tragedy - but one that presumably will pass once we collectively discover it. If not, then it’s just nostalgic.
It's hard to say. Perhaps LLMs of tomorrow will become capable enough to fix the mistakes of LLMs today. If so, great -- I'm worried about nothing.
If not, we could see that LLMs of tomorrow struggle to keep up with the bloat of today. The "interest on tech debt" is a huge unknown metric w.r.t. agents.
This. There’s no limitation to your prompting. If you feed rules and patterns for clean code to a bunch of agents they’ll happily work on that level.
Just right now no one cares enough yet. Give it a year or two.
I could conceive something evolving on a different abstraction layer - say, clean requirements and tests, written to standard, enhanced with “common sense”