Don't get me wrong, LLMs are way better than me at most things, but I don't think you can deny that the current generation of models makes questionable decisions sometimes. Especially on project structure, API boundaries, and code duplication. I also think they just have bad taste in general, though of course that's more subjective.

▲

tokioyoyo 2 hours ago | parent | next [-]

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.

▲

swatcoder 2 hours ago | parent [-]

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.

	▲	tokioyoyo 23 minutes ago \| parent [-]
		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.

▲

trio8453 2 hours ago | parent | prev [-]

> I don't think you can deny that the current generation of models makes questionable decisions sometimes

Sometimes, not enough to believe you that you can do it better. And even if you could, to believe that it's overall worth it to work in that way.

▲

fasterik 2 hours ago | parent | next [-]

You can work the way you want to work. In my experience, letting the agent make every decision leads to a big ball of mud that requires touching dozens of files to make a change. More context is needed, it burns through tokens much faster, and the agent takes shortcuts and builds technical debt. So the way I prefer to work is to have changes targeted to a single file or small set of files where I've defined the API. Maybe that will change in the future, I'm not set in stone here.

▲

zmmmmm an hour ago | parent [-]

> In my experience, letting the agent make every decision leads to a big ball of mud that requires touching dozens of files to make a change

It seems too early to make any conclusion like that. We've still only been doing agentic coding for a year and capability significantly improved during that time. I don't think anybody on either side of this debate can have actual empirical evidence to support conclusions about where it lands longer term.

The main argument I see is that it probably pays to be slightly conservative because the cost of being wrong by maintaining too much oversight and shipping slightly less code is better than the cost of ending up with an entirely unmaintainable system. In some cases it will be more than "slightly less" but in almost all complex pre-existing systems, you are rate limited by a lot of other factors outside of code production, so the effective difference just isn't that high.

	▲	solidasparagus 5 minutes ago \| parent \| next [-]
		At agentic coding velocity, tech debt becomes obvious much more quickly. Empirical evidence is a bit of a ridiculous bar to hold for software development - we are as quantitatively blind now as we have ever been - but at least for me the anecdotal evidence is very clear. Today's agents hill-climb and their software architecture is pretty reliably bad without a human in the loop. And it's debatable how much better they will get quickly. Verifiable rewards for maintainability of software is, I think, possible but very hard.
	▲	fasterik an hour ago \| parent \| prev [-]
		When I said "in my experience" I meant literally that, my experience so far. I'm not making any predictions. I'm definitely anticipating things improving at a rapid pace, which is why I think it's good to run frequent experiments. If in a month I find that an agent can one-shot a 20k line project without creating an unreadable, unmaintainable mess, that will be great.

▲

NorwegianDude 8 minutes ago | parent | prev | next [-]

To be fair, if LLMs were good at decisions, we would not need people.

▲

jonplackett 2 hours ago | parent | prev [-]

What still is true for all fields of LLMs: if you can’t tell they do it suboptimally, you are just not that knowledgable in that area.

It still applies to all things LLms can do from law to code to art to ideas.

They can do it - and very acceptably - but only to the untrained eye.