Any project is a sum of its parts, and if you’re talking about maintainability, then the parts you could easily point to would be things like high coupling, overly large file sizes, functions that are too big and should be broken up.

Meanwhile, your own link shows that it’s roughly within the ballpark of industry average. And if you look through issues for any large project on github you’ll see similar types of issues. Given how new the project is, none of this is really surprising or out of the ordinary.

As a note, nowhere did I suggest they do manual code reviews of everything at this speed. What I do think they have is a regression test suite which they build out as issues come up and they fix them.

I keep hearing people talk about trust, and it’s really doesn’t make sense to me because we’ve never done software development based on trust. Humans make mistakes all the time, and I’ve seen plenty far worse human code than anything an LLM has crapped out over my career. The way we ensure quality is through having a process. It’s done by having good specifications, testing, code reviews, planning, and so on. All these things equally apply to code written by hand and that’s generated by an LLM, and trust has nothing to do with it.

Can you point to which part specifically are you referring to here? https://github.com/storytold/photocraft

That’s only true for the US though. Electricity costs in China are a third of what they are in the states, and open models are now becoming very competitive. We can also see here that DeepSeek is already close to breaking even. The other factor is that models continue to get more efficient, and even local models like Qwen 27b can do serious work. Especially, when combined with good tooling. A coding harness that uses Qwen with five different roles scores as well as Anthropic Fable on the benchmarks.

I’ve been using them happily, and they do what I need. So, to me, this is real useful software that’s replacing proprietary solutions.

Large corps always end up implementing shitty practices because business practices are driven by pencil pushers. Even before LLMs, some of the most soul crushing jobs were found at large corps working with shit like J2EE. That’s nothing new really.

At my job, we use LLMs, but nobody is making 2k loc PRs all of a sudden, and we still pair up to review code, and generally work at human speed.

The only studies I’m aware of used tiny samples and produced muddled conclusions. If you have some conclusive empirical research then do feel free to share it though. Meanwhile, using LLMs doesn’t mean doing less, it just means focusing on different things. The skill deficit here is the same kind as the skill deficit people have using punch cards or writing assembly by hand today. As more aspects of coding become automated, different things become relevant and that’s what people shift their attention to.

I’ve seen no evidence of that so far. I also fail to see how writing code practices are related to the review and quality control process. These things aren’t linked in any way that I’m aware of.

Assuming that Linux kernel team continues to use the same review process they always had, there’s zero reason to think that there would be an increased rates of bugs due to LLM generated code. This seems to be something people without programming experience don’t understand. Code quality isn’t premised on trust, it’s a product of the development process. Projects ensure quality by having specifications, tests, doing code reviews, and so on. As long as the practices the kernel team has established continue to be applied, they will catch the bugs made by LLMs or humans exactly the same way.

Maybe if it was a publicly owned utility then sure. I wouldn’t even trust a non profit here.

You have absolutely no clue how LLMs work. It’s a neural network generalizes patterns that get imprinted onto it during training. And then these patterns are expressed in the given context during inference. People tend to confuse the output looking similar to training data with the mechanism being simple retrieval. While these agents do not think or feel, describing what they do as storing things in a database and pulling them up later is grossly incorrect. This framing fundamentally misrepresents how LLMs actually store and retrieve information.

There is no database or a lookup table, and there is no copy of any text they were trained on tucked away somewhere inside the weights. What they have is a compressed statistical model of the patterns that exist across trillions of tokens the text was broken down into. When you ask an LLM a question it does not go find the relevant passage and regurgitate it. What actually happens is that it generates text token by token based on the probability distribution it learned during training. It’s more akin to the way state machines like Markov chains work.

If anything, the way LLMs work is actually much closer to how humans improvise or combine ideas than to how a search engine or database works. When you write a sentence, you don’t pull up a specific sentence you memorized from a book and copy it. You’ve absorbed the patterns from countless examples of language over your lifetime and internalized them. Writing is a process of generating novel combinations based on those patterns.

Similarly, the weights of a model encode statistical regularities about word co occurrence, syntactic structures, semantic relationships, and higher level conceptual patterns. When it generates text it is combining those patterns in ways that were never present in the training data. That’s how LLMs produce entirely novel sentences that have never been written before, and why they can be prompted to combine ideas from different domains in creative ways.

LLMs do reproduce training data verbatim in some cases, but this happens because of overfitting on rare or repeated sequences. When a specific string appears many times in the training data like a famous quote or a common error message the model learns to assign an extremely high probability to each token in that exact sequence. So when it generates it follows the most likely path to reproduce the original text. It is similar to how a human can memorize a song or a poem by hearing it many times but that does not mean our general language ability works by pulling up stored copies from memory.

The notion that LLM assisted coding is equivalent to ordering from the menu at a restaurant is laughably naive. You seem to think that it’s like a slot machine where you put a query in and then you either get a correct result or some nonsense and you have to try again.

The way this process actually works is that you start by understanding the problem and figuring out how you want to solve it in terms of architecture, data structures, and algorithms that will be used. Then you get the LLM to come up with a rough shape of the solution, and iterate on it until it works the way you want. In practice, it’s like working with a genetic algorithm.

The core skill in using these tools is the same as the skill you need when writing code by hand. You have to understand the given requirement, the shape of the solution, and how to verify that the code that was produced actually matches the intent.

It’s ironic that you talk about AI only copying while uncritically regurgitating nonsense yourself.

People who built their whole identity around hating LLMs really do need to get a new hobby.

This is just such an idiotic line argument. It’s as if StackOverflow didn’t exist before LLMs and there weren’t whole memes about copy/paste driven development. You’re literally making the same argument as RIAA here, and if you don’t understand how absurd it is then there’s no helping you.

not my fault your instance can’t federate properly

I love that you’re so mad now that you’re actually stalking me 🤣

Nah, pretty sure the dumbo posting about the AI cult in burgerland only thinks about burgerland.

lmao you keep on waiting for your China collapse narrative to come to pass kiddo

tell me more about this ‘AI bubble’ in China dumbo

https://hai.stanford.edu/news/inside-the-ai-index-12-takeaways-from-the-2026-report

Wow, imagine being so ignorant to think that this tech isn’t developed outside burgerland.