Comment by will__ness
17 hours ago
> But there are serious limits. [Your coding agent] will lie to you, they don't really understand things, and they often generate bad code.
I think that really high quality code can be created via coding agents. Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing.
Its still engineering work. The code still matters. Its just a different tool to write the code.
I'd compare the difference between manually coding and operating a coding agent to the difference between a handsaw and a chainsaw - the end result is the same but the method is very different.
> the end result is the same but the method is very different.
I dont think anyone really cares at all about LLM code that is the exact same end result as the hand written version.
It's just in reality the LLM version is almost never the same as the hand written version, it's orders of magnitude worse.
> it's orders of magnitude worse
This is not my experience *at all*. Maybe models from like 18+ months ago would produce really bad code, but in general most coding agents are amazing at finding existing code and replicating the current patterns. My job as the operator then is to direct the coding agent to improve whatever it doesn't do well.
So far, I haven't seen any comparison of AI (using the best available models) and hand written code that illustrates what you are saying, especially the "it's orders of magnitude worse" part.
In the limited use cases I've used it, it's alright / good enough. But it has lots of examples (of my own) to work off of.
But a lot of people don't think like this, and we must come to the unavoidable conclusion that the LLM code is better than what they are used to, be their own code, or from their colleagues.
Speak for yourself.
I mean yes, i am speaking for myself. I am drowning in mountains of LLM slop patches lol. I WISH people were using LLMs as "just another tool to generate code, akin to a vim vs emacs discussion."
9 replies →
> Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing
Lots of times I could just write it myself and be done with it
Sure and lots of times I can walk places. That doesn't mean bikes, cars, trains and planes aren't incredibly useful. They let me achieve things I can't in other ways for example transporting cargo without a team of people to help me. Just like AI coding.
Yet replacing walking with cars is often cited as one of the reasons for many of society's ills.
2 replies →
Maybe your analogy holds if driving and walking took the same amount of time.
Plus "planning, implementing, validating, and reviewing" would be a bit like walking anyway in your analogy.
Would you still use your car if you ended up in the wrong destination half the time?
4 replies →
>I think that really high quality code can be created via coding agents. Not in one prompt, but instead an orchestration of planning, implementing, validating, and reviewing.
Do you have any advice to share (or resources)? Have you experienced it yourself?
Here is my exact workflow: https://willness.dev/blog/claude-code-workflow
The practical limit is the latency and inference cost. A full planning and validation loop burns a lot of tokens, and waiting for that cycle breaks flow compared to just writing the code.
Only if your flow is writing the actual code.
If you flow state involves elaborating complimentary specifications in parallel, it's marvelous
> high quality code
What does high quality code look like?
> The code still matters.
How so?
Great questions. For me, high quality code is code that: 1) works (is functional, no bugs) 2) is secure (no security vulnerabilities) 3) is extendable (I can quickly and easily build new features with limited refactors)
I argue the code still matters because of these 3 reasons. If the code doesn't work, your product won't work. If its not secure, there's obvious consequences. If you can't build new features quickly, you will end up wasting money/time.