I’d say I fall in the “AI skeptic but willing to use it” category. If LLMs can actually clean up after themselves it would actually be a game changer.

▲

jerf 3 hours ago | parent | next [-]

LLMs can clean up after themselves if you steer them. It's not very hard. I often have a two-step dance I do where the LLM first outputs some code and then I prompt it to fix the types up to my standards. I haven't found a way to prompt it with any number of skills or CLAUDE.mds or anything else to get it to do it the way I want on the first pass, but it's not that hard to just fix it afterwards. It's a fast enough process that it feels fine using it. One can even make a case for it being a decent way to operate anyhow; make a sketch, then firm it up isn't entirely unlike my manual coding process was anyhow.

The main problem is that pointing an LLM at a codebase and telling it to just "make it better" taps out pretty quickly. That is, not that there's zero juice to squeeze there, but there's not a ton. You can get a bit of improvement but it also rapidly starts changing things just to change things, which I'm not even going to complain about all that much because there's a sense in which it is simply doing as you asked.

So you still need human taste and direction. This will be especially true for something the size of that codebase where you can only hold small fractions of the actual code in the context window at once. Summaries only get you so far.

▲

andai 2 hours ago | parent | next [-]

I asked an agent for some high level cleanup and refactoring. I found that I ended up disagreeing with most of the structural changes. Some of them were necessary, some were beneficial, but largely it turned straight line code into abstract factory manager type stuff.

More broadly I've found that making code more elegant (e.g. by removing duplication) increases the cognitive load, because now you can't just read the code anymore but need to mentally "decompress" the higher level structures and indirection into the straight line code, the "code that actually runs."

	▲	jerf 19 minutes ago \| parent [-]
		If it wasn't clear, I don't ask the agent to "clean up my code". I ask it to "take this map[string]string you pass around with constant keys and turn that into a structure" or "extract this API provider out into an interface and make everything using it use this interface instead" or other concrete instructions. LLMs, to a first approximation, already did as well as they could on the first pass. You can get a bit more out of them by asking them to just try harder, but not much. Whereas if you go in with specific changes they are pretty good at implementing them. This especially matters because my personal style deviates from the common practices. This may also be why I can't get it to just happen by prompting for it. But if you walk it through it's perfectly capable of transforming the code into a better style, and it's still way faster than trying to write it from scratch.

▲

maccard 2 hours ago | parent | prev [-]

> LLMs can clean up after themselves if you steer them. It's not very hard. I often have a two-step dance I do where the LLM first outputs some code and then I prompt it to fix the types up to my standards.

My experience has been the opposite. I prompt it and it generates something that mostly works, but steering it into something that would actually be maintainable is an exercise in futility. GPT-5.5 uses up my entire allocation of tokens in just reading the context docs and doing a single shot task.

> aven't found a way to prompt it with any number of skills or CLAUDE.mds or anything else to get it to do it the way I want on the first pass, but it's not that hard to just fix it afterwards.

I've yet to find a way to get an LLM to actually follow the instructions in CLAUDE/Agents.md It very quickly gets to a point where it forgets explicit instructions such as "run clang-format on all .h/.cpp files that you touch", and saying "our coding standards can be found at <link to Notion/Confluence>, please ensure all code adheres strictly to this standard" is ignored. I'd also say that the first pass of the code is very often not even close to how it _should_ be implemented so it's not just review and patch up, it's rearchitect + restructure 50% of the code.

> it also rapidly starts changing things just to change things,

Agreed. LLM's are (very good) text generators. They are good for generating code, and left to their own devices they will generate and generate and generate. Getting them to edit, simplify, and foresee future problems is something that people keep saying "use the latest model, it's amazing (despite saying that about the last 3 models" or "you just need to use <harness|framework>" or "your agents.md needs to contain XYZ" will solve.

▲

jerf 15 minutes ago | parent | next [-]

"My experience has been the opposite. I prompt it and it generates something that mostly works, but steering it into something that would actually be maintainable is an exercise in futility."

I've seen others have this experience, too.

It would be interesting to sit us down next to each other for a day or two and compare how we do things, but I suspect much less than that won't reveal much of interest.

It is weird to me how often I have to remind the models about their skills or CLAUDE.md (or equivalent). Though I've sort of taken it as just another way I can impact the process, because sometimes I'm happy for them to forget a particular skill for a moment... particularly when I want it to just do a thing based on my prompt and it decides to invoke the "OK let's design this super carefully" skill. I've gotten a lot of use out of that one but I'm pretty comfortable having to explicitly invoke it.

▲

jasonlotito an hour ago | parent | prev [-]

> I've yet to find a way to get an LLM to actually follow the instructions in CLAUDE/Agents.md

I'll give you a hint: do you rely on people to do the right things, or do you have automated unit, integration, and e2e testing? Do you have linters? Do you have static analysis that automatically runs and will block when violated?

If you are verifying humans, why aren't you verifying LLMs?

	▲	maccard an hour ago \| parent [-]
		Yes, and agents are generating code that fails those checks regularly. I wouldn’t accept a junior engineer saying “oh I just submit my code and see if the tests pass, let me know if they’re failing and I’ll fix them”. Pre commit hooks are disable-able and LLMs have shown they’re more than willing to say “tests were failing before this change” when they weren’t, or to use python scripts to self escape their sandbox restrictions.

▲

onlyrealcuzzo 4 hours ago | parent | prev | next [-]

I'm about to release some tooling that's been very effective for me.

Essentially, there's a few ways LLMs write "bad" code that is different from how people write "bad" code.

We've got pretty good tooling to catch the ways people write bad code - it just happens to be much easier to do with static analysis (and is less noise prone).

The ways LLMs write bad code is typically 1) bad architecture - hard to detect in the ways that are really important, 2) unnecessary state and control flow (and decisions based on state), 3) bad / inadequate tests.

Methods to detect these problems have existed for ages, but they've never caught on because it's typically too difficult to tune them to have high signal / noise for humans, and AFAIK - no one else tried putting them all together and seeing how LLMs work with it.

LLMs are great at sorting through signal / noise -> so you can help surface potential issues with metrics that would be too noisy for humans, but seems to work pretty well for LLMs to find the source of architectural problems and design better solutions (from my experience - may be biased, I built the tooling to literally solve this problem for the main project I'm working on).

▲

andai an hour ago | parent | next [-]

Can you elaborate on the tests thing? I'm new to testing, and AI agents recently voluntarily added an large number of tests to one of my projects. I've been learning a lot by reading them, and it seems like a great habit to develop.

But they're also writing some very strange code and some very strange tests. I don't know what good practices look like here, so when something looks strange to me I can't trust my own judgment, whether it's actually smelly or just a pattern I'm not used to yet.

On a side note, I recently had an agent implement a major architectural change. It turned out to have done it completely backwards, in a way that was pointless. (Improved nothing and actively made things worse.) However it had supplied generous tests for the new code, and of course all the tests passed...

So it had "proven the correctness" of something which was completely incorrect.

I later realized that even formal verification would not have prevented this. It would have just written a mathematical proof that the wrong code was correct.

▲

mirekrusin 4 hours ago | parent | prev [-]

You forgot to include link to your tool.

	▲	all2 2 hours ago \| parent \| next [-]
		If I had to do a 'code quality' checker I think I'd try to use some combination of syntax tree analysis, data flow analysis, and LOC changed. Something like that. Too many new nodes in the syntax tree, or a sub-tree that appears sufficiently similar to another sub-tree (for various definitions of similar), data-flow/side effects gets more convoluted, too many LOC, and so on.
	▲	onlyrealcuzzo 2 hours ago \| parent \| prev [-]
		An LLM could probably figure out how to use it now. But it doesn't yet have a coherent UX unless you're me. Hopefully, I'll iron that out over the next week and I'll update you.

▲

owaislone 2 hours ago | parent | prev | next [-]

You have to treat it like a co-worker send you PRs for review. You review, ask to improve/cleanup stuff and it'll follow up. You can even ask it to remember so it follows the patterns in future. Even better, if you work with it to come up with a design first and then send it coding, you often don't need as much cleanup as the desired architecture is agreed upon early.

▲

maccard 37 minutes ago | parent [-]

I would tell my co worker “this code has so many issues that I’m not actually reviewing it. Please make sure it meets the project standards before sending it back to me”if it happened twice I’d talk to their manager.

	▲	owaislone 35 minutes ago \| parent [-]
		Sure - define your project standards in the repo or agent's skill and tell it just that.

▲

figmert 4 hours ago | parent | prev [-]

They can. You just have to steer them

	▲	maccard 44 minutes ago \| parent [-]
		Can you share a transcript of an LLM generated feature/bug fix that you steered into being good quality?