You can get AI to generate the best code you have ever seen. It just takes time and direction. I can write "poetic" code, but it takes orders of magnitude more time. I can also write beautiful code with AI, but it is also time and brain intensive.

It generates terrible code when used in a nearly open loop manner, which all coding agents are currently doing.

And look what damage comes from that human generated code.

Now we get hyper mass production of the same quality.

Hard to argue with that.

"No one cares about code quality" - disagree. As a dev, I care about code quality in that shitty code makes my life suck.

As a user of terrible products, I only care about code quality in as much as the product is crap (Spotify I'm looking at you), or it takes forever for it to evolve/improve.

Biz people don't care about quality, but they're notoriously short sighted. Whoever nerfed Google's search is angering millions of people as we speak.

"Code quality" here isn't referring to some aesthetic value. Coding agents write code that doesn't converge, meaning code that they cannot evolve after a while. They get to the point where fixing one bug causes another, and then the codebase is in such a state that no human or agent can salvage.

People who say they don't care about the quality of code produced by agents are those who haven't been evolving non-trivial codebases with agents long enough to see just how catastrophically they implode after a while. At that point, everyone cares, and that point always comes with today's agents given enough lines and enough changes.

Nobody cares about costs until they pay them themselves.

Regarding code quality and tech debt, it's sensible not to care if it doesn't lead to anything observable. Do you really care of some "bad" code somewhere that hasn't changed for 5 years but keeps working fine, and has no new requirements?

On the other hand, if you work on an active codebase where fixing one bug inevitably leads to another, maybe it's worth asking whether the code quality is simply too low to deliver on the product expectations.

It's not even obvious to me in which direction coding agents move the needle. Do you want higher quality, at least at a higher (design) level, when you heavily use agents, so that you know know the mess will at least compartmentalized, and easier to deal with later if needed? Or do you just assume the agent will always do the work and you won't need to dig into the code yourself? So far I've mostly done the former, but I understand that for some projects, the latter can make sense.

It really shows that nobody cares about uptime at github or the jankiness of claude.

I wouldnt say that customers are indifferent, but it wouldnt be the first time that investor expectations are prioritized far above customer satisfaction.

I thought the sales pitch of all of this is that the AI was supposed to relieve people from having to do a bunch of annoying bootstrap coding and to do it in a way that we could extended easily.

I have a subscription to Claude Code and despite my skepticism, it has been pretty good at just getting a goofy PoC thing going. When I look at the code, it’s usually insane unless the prompt was so narrow and specific like about writing a function that does one thing and only one thing.

Outside of small, personal projects, I am still really uncomfortable at having agents run wild. I see the result, and then I spend a bunch of time having to gain the context of what is going on, especially if I ask it to implement features in spaces I have general knowledge, but not expertise. So, the problem remains the same. These things still need handholding by people who understand the domain, but having people become glorified PR reviewers is not an acceptable path forward.

Arguing that there is lots of bad production code kinda avoids the actual issue that is going on here. Yes, a lot of sloppy code can and has been written by people. I’ve seen it myself, but it feels like the actual thing is that, we are now enabling that at scale and calling it “abundance” when instead we are really generating an abundance of completely avoidable security holes and logic errors.

Does the pressure affect the LLM's judgement in the same way it does a developer whose job is on the line?

Have you tried just asking CC to make a codebase more elegant? It’s surprisingly effective up to a point. No reason to think that won’t work better down the road.

> I think that the prompt is the thing that should be PR'd at this point, because ultimately the spec is what's important.

The fundamental problem there is the code generation step is non-deterministic. You might make a two sentence change to the prompt to fix a bug and the generation introduces two more. Generate again and everything is fine. Way too much uncertainty to have confidence in that approach.