I’m not sure how to say this without sounding smug, but the last year has shown that most of those things just… don’t matter. It’s just the next level of the “variable naming PR comment battle”, so will become obsolete very soon.
Obviously there are mission critical systems where it matters, but if “your code can be A/B tested” or “slowly rolled out”, chances are, it doesn’t matter.
You'll find that design matters when token spend starts facing real accounting.
Tech debt is still tech debt, even if there exist models that can wade through, because it's going to require increasingly sophisticated models navigating increasingly large context windows and increasingly speculative workspace operations to keep making progress on it.
Vendors like Anthropic and OpenAI are laying a pit trap when they demonstrate how their models can independently code their whole platform as it becomes increasingly byzantine and inscrutable because not only do they benefit from internal/prerelease models but they have effectively unlimited spend because all that spending acts as a lure to draw you into their trap.
For everybody else, design still matters. People are just working really hard to make you forget.
Personally I think I could probably be content for the rest of my days running something like Z.ai glm-5.3-flash locally, so I'm not that worried about the token spending (and still can't understand how OAI/Anthropic/etc convinced the market they have any kind of moat to motivate those kind of evaluations, but that's another topic...)
That said, I also feel like betting on readability, maintainablility, taste, etc, being an important aspect of software, at least until code will remain some sort of human readable artifact. We'll still want to be able to understand it and perhaps occasionally add/edit by hand, make sense of it without trusting blindly what any kind of program (LLM based or not) will tell us about it, and so on.
The problem here is not the vendors.
The "problem" is that design mattered when producing code was a truly manual effort. Writing things down, aligning specs, design, contracts, all of that would mold what could come next.
Now ANY design from amazing to terrible can be regenerated and generated dozens of times over for literal single digit dollars.
Cost of tokens is NOT a problem unless you have a codebase with hundreds of person-years of effort. Not many people do.
Honestly, I keep hearing this argument, but the past 2 years have shown the opposite. OAI/Ant are not the only companies providing inference.
There are legitimate FAANG-like companies that have general guidelines about “when to use Fable/GLM/DS” and etc. to keep the costs down. And I think it’ll continue that way.
You didn't address the argument about tech debt. How do you get the greatest quantity of maintainable, high quality code within a given token budget? The answer, at least so far, seems to be human experts in the loop. We've also been hearing for years that LLMs are going to automate away software development entirely, but software job postings are steadily rising.
>How do you get the greatest quantity of maintainable, high quality code within a given token budget?
Doesn't matter as much. The cost of "maintenance" is going down, from what I can see internally, from other companies, and every story i'm reading from other organizations as well. Token budgets are changing, but model quality and effectiveness are going up as well.
> We've also been hearing for years that LLMs are going to automate away software development entirely, but software job postings are steadily rising.
I think this has been contested from day 1. SE jobs might be automated, but jobs might increase, if there's possibility of starting new companies / new investments / etc.
I'm still not clear on what you're really saying. If a human programmer's input doesn't matter at all, then anyone should be able to prompt a model until it spits out the software they want. That might work today for building fun tech demos, but I don't see it happening on projects that have a minimum bar for security/reliability and long-term maintenance. Would you say, for example, a team of 10 managers with no software experience can be as successful as a team of 10 expert programmers at building a large project like an operating system, with both teams having access to the same AI models and budget?
No, because expert programmers will not know what they’re building, and skew the prompts and ask for the right things.
The analogy would be math people with AI vs. non-math people with AI trying to solve some problems. I cannot solve the problems because I have no idea how to prompt it to go specific way. But it doesn’t matter how dirty your scratchpad was, because you got to the solution.
> I don't see it happening on projects that have a minimum bar for security/reliability and long-term maintenance
I don’t get this, because this is currently, right now, at this second, happening across huge projects. My point was that maintainability is less of an issue than before. Also, frankly, over years, I’ve seen bad code that AI wouldn’t even write. So there can be a case that the maintainability/code quality isn’t even going down as the models get better.
API design matters if anyone outside your app consumes it. Duplicate code makes changes hard and most compilers can't optimize it away. Bad file structure wastes tokens and makes off target edits more common.
These things are important even in a repo with zero human code. A project that's filled with tech debt will always be hard to work with no matter what latest frontier model you're using.
I think a lot of this can be automated with slop detectors that flag messy unreadable code and make agents rewrite it, but you can't say it doesn't matter.
Obviously there are mission critical systems where it matters, but if “your code can be A/B tested” or “slowly rolled out”, chances are, it doesn’t matter.