I wonder what happened to the person that wrote "Coding as Creative Expression" (https://build.ms/2022/5/21/coding-as-creative-expression/)?

I'm not (just) being glib. That earlier article displays some introspection and thoughtful consideration of an old debate. The writing style is clearly personal, human.

Today's post is not so much. It has LLM fingerprints on it. It's longer, there are more words. But it doesn't strike me as having the same thoughtful consideration in it. I would venture to guess that the author tried to come up with some new angles on the news of the Claude Code leak, because it's a hot topic, and jotted some notes, and then let an LLM flesh it out.

Writing styles of course change over time, but looking at these two posts side by side, the difference is stark.

The copyright angle is the most underrated part of this story. Anthropic built their models on other people's code under the fair use argument, but the moment their own code leaks they reach for DMCA takedowns. You can't have it both ways. The clean room reimplementations are the natural consequence of the legal framework they themselves advocated for.

I personally found it really amusing how they weaponized the legal system to DMCA all the claude code source code repositories. Code ingested into the model is not copyrightable, but produced code apparently is when by legal definition computer generated code can not be copyrighted and that's one of their primary arguments in legal cases.

> Many software developers have argued that working like a pack of hyenas and shipping hundreds of commits a day without reading your code is an unsustainable way to build valuable software, but this leak suggests that maybe this isn’t true — bad code can build well-regarded products.

The product hasn't been around long enough to decide whether such an approach is "sustainable". It is currently in a hype state and needs more time for that hype to die down and the true value to show up, as well as to see whether it becomes the 9th circle of hell to keep in working order.

> It should serve as a warning to developers that the code doesn’t seem to matter, even in a product built for developers.

Code doesn't matter IN THE EARLY DAYS.

This is similar to what I've observed over 25 years in the industry. In a startup, the code doesn't really matter; the market fit does.

But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather than innovation.

> But then the clean room implementations started showing up. People had taken Anthropic’s source code and rewritten Claude Code from scratch in other languages like Python and Rust.

Seems like the phrase "clean room" is the new "nonplussed"... how does this make any sense?

Seems equally valid to come out of this with the takeaway that code quality _does_ matter, because poor coding practices are what led to the leak.

Sure, the weights are where the real value lives, but if the quality is so lax they leak their whole codebase, maybe they are just lucky they didn’t leak customer data or the model weights? If that did happen, the entire business might evaporate overnight.

Claude Code proves you don't need quality code — you just need hundreds of billions of dollars to produce a best-in-class LLM and then use your legal team to force the extreamly subsidised usage of it through your own agent harness. Or in other words, shitty software + massive moat = users.

Seriously, if Anthropic were like oAI and let you use their subscription plans with any agent harness, how many users would CC instantly start bleeding? They're #39 in terminal bench and they get beaten by a harness that provides a single tool: tmux. You can literally get better results by giving Opus 4.6 only a tmux session and having it do everything with bash commands.

It seems premature to make sweeping claims about code quality, especially since the main reason to desire a well architected codebase is for development over the long haul.

I dont understand why so many people have the need to emphasize the code vs product battle. There is no battle. Coding/developing/software engineering is a skill, that just like any other skill has certain requirements and best practices that have to be followed in order to make a quality, maintainable and adaptable application that can stand the test of time from the software perspective. Product, features, marketing bla bla that is entrepreneurship part, and is not related to software, other than directing the software requirements,but not beacuse product people think about requirements, but instead just because they come naturally from the required features they envision.Just because programmers can write code doesnt mean they can ship good products.Just because a plumber can lay pipes doesnt mean he can run his own company or invent a new way of laying pipes. But I will tell you that a bad plumber who lays pipes and doesnt know how to connect them, bend them or shield them will surely have inferior product/service in the long term. And by the way, success of a company is measured over time, we will see where claude code will be in 10 years time when the hype dips a little, then we can say yeah the code was bad but everyone loved it and uses it still. I mean they leaked entire code online and this guy says yeah code was bad but who cares, what world are we living in? The fact that anything got leaked is a serious breach of best practices and security also at this point, something a company that used to work for DoD(W) shouldnt be doing, it can even be considered a national threat at this point. I know mistakes happen, I do them all the time, but then again the 'best' companies should be almost immune to mistakes cause stakes are high.But of course, move fast and break things is more important.Am I wrong?

> bad code can build well-regarded products.

Yes, exactly. Products.

It seems like me and all the engineers I've known always have this established dichotomy: engineers, who want to write good code and to think a lot about user needs, and project managers/ executives/sales people, who want to make the non-negative numbers on accounting documents larger.

The truth is that to write "good software," you do need to take care, review code, not single-shot vibe code and not let LLMs run rampant. The other truth is that good software is not necessary good product; the converse is also true: bad product doesn't necessarily mean bad software. However there's not really a correlation, as this article points out: terrible software can be great product! In fact if writing terrible software lets you shit out more features, more quickly, you'll probably come ahead in business world than someone carefully writing good software but releasing more slowly. That's because the priorities and incentives in business world are often in contradiction to priorities and incentives in human world.

I think this is hard to grasp for those of us who have been taught our whole lives that money is a good scorekeeper for quality and efficacy. In reality it's absolutely not. Money is Disney bucks recording who's doing Disney World in the most optimal way. Outside of Disney World, your optimal in-park behavior is often suboptimal for out-of-park needs. The problem is we've mistaken Disney World for all of reality, or, let Walt Disney enclose our globe within the boundaries of his park.

> The object which labor produces confronts it as something alien, as a power independent of the producer.

And this is why so much software today runs extremely hot.

It's creators clearly care not for the efficiency of how it is built, which translates directly into how it runs.

This blog post is effectively being apologetic about the fact that this is alright, since at least they got product market fit. Except Anthropic is never going to go back and clean up the mess once (if) they become profitable.

I doubt anyone will like how things will be in 5 years time if this trend of releasing badly engineered spaghetti continues.

In my opinion, the “code is garbage” argument is a moot point. Anthropic is in the business of removing humans from the SDLC. As long as their models can understand and update the code they generate it can remain garbage. They’re not optimizing for human comprehension of the output. They don’t even want you looking at it. And eventually the models will get good enough that you won’t have to.

The five-layer permission system discussion is interesting from a governance angle. Most small teams deploying Claude Code have no idea those permission layers exist — they approved the tool based on the marketing page, not the actual trust model.

The practical question for any CEO: if your developer's machine is running an agent with filesystem access, do you know what it can touch? The leaked code shows the answer is more nuanced than "it only touches what you tell it to."

Wrote a non-technical breakdown of what this means for AI tool policy (specifically the autonomous permissions mode and memory system that were hidden behind feature flags): https://www.aipolicydesk.com/blog/claude-code-leak-what-ceo-...

I feel the conclusions here are a bit thin.

Code quality tends to have an impact on more than just aesthetics - and Claude Code certainly feels like a buggy mess from an end user's perspective.

Of course people still use Claude Code, but that is certainly because of the underlying models first and foremost. Most products don't have such a moat and would not nearly see as much tolerance from end users. If the Max subscriptions could be used with other harnesses, I am sure Anthropic would have to compete harder on the quality of the harness (to be fair, most AI based tooling seems pretty alpha these days, but eventually things will stabilize).

Polish is not everything, clearly, but it is a factor, and I feel Claude Code is maybe the worst example to use here, as it doesn't at all generalize to most other products.

Points from the article.

1. The code is garbage and this means the end of software.

Now try maintaining it.

2. Code doesn’t matter (the same point restated).

No, we shouldn’t accept garbage code that breaks e.g. login as an acceptable cost of business.

3. It’s about product market fit.

OK, but what happens after product market fit when your code is hot garbage that nobody understands?

4. Anthropic can’t defend the copyright of their leaked code.

This I agree with and they are hoist by their own petard. Would anyone want the garbage though?

5. This leak doesn’t matter

I agree with the author but for different reasons - the value is the models, which are incredibly expensive to train, not the badly written scaffold surrounding it.

We also should not mistake current market value for use value.

Unlike the author who seems to have fully signed up for the LLM hype train I don’t see this as meaning code is dead, it’s an illustration of where fully relying on generative AI will take you - to a garbage unmaintainable mess which must be a nightmare to work with for humans or LLMs.

I think this misses the target.

First, the twitter quote is standard toxic clapback nonsense. Gambling makes billions and does not add any value. Even facebook can argue it adds more value than gambling so this one is a dud.

People use claud code because of claud the model and not claud the harness. Cursor or a hacked up agent loop using opus or whatever are about as good. The magic is in the model not the harness here. This isnt to say the hardness is doesnt do anything.

The other bit this misses is that yes the product matters more then the code, and if the product burns battery/ram/etc doing nothing because the ai has crappy code or maybe something leaks or has a security issue, then that impacts the product.

Reminds me of a question that I asked couple of years ago - https://news.ycombinator.com/item?id=37176689

I think the argument here ignores a critical fact: a huge factor in Claude Code's popularity is the Claude Max plans. These plans give you potentially thousands of dollars of tokens for a capped $200.

Speaking for myself, I long for the day I can dump the comparatively garbage experience of Claude Code for something more enjoyable and OSS like OpenCode. But the fact is that it is simply not economically viable to do so.

So the PMF is not really for Claude Code alone -- it is for Claude Code + Claude Max.

I don't think it's vibe coded garbage. Sure, the 3000-line print.ts is terrible, but there's some good patterns in there that were definitely prompted in by some experienced engineers -- the feature flag setup, the `..I_VERIFIED_THIS_IS_NOT_PATH_OR_CODE` funny type hints, the overall structure. Just the usual signs this started as a PoC but quickly evolved into something much bigger. The codebase is a really interesting read.

From a moral perspective, I would argue that this is still theft of IP, even if it's a "clean room reimplementation". The code carries valuable information about what works and what doesn't — knowledge that Anthropic had to discover through real work and iteration. It's the same as a Chinese factory duplicating a product: they skipped the entire R&D phase and saved time and money.

Code quality matters when it becomes the code you have to maintain after six months. I'm honestly surprised by how some features of Claude Code seem to be held together with gum and duct tape.

That being said, if you're just beginning and looking for your market fit, or pitching to investors with a flashy demo, it doesn't need to be an architectural miracle, in fact it will waste your time.

Saying that code quality doesn't matter is simply false, if people enjoyed Claude code so much, anthropic wouldn't have to block direct API access to users.

Their "product market fit" is the LLM model itself, not the harness. The harness is completely replaceable in my opinion, it's just that Claude is the cheapest way to access the models.

" The real value in the AI ecosystem isn’t the model or the harness — it’s the integration of both working seamlessly together. "

Wut? The value in the ecosystem is the model. Harnesses are simple. Great models work nearly identically in every harness

Afaik you can run Claude Code locally but every single demo i see uses it exclusively with apis, so are the local models already good enough to be worth it or is the only reasonable use for claude code with cloud models?

OP should expand on #1, why he thinks it’s garbage. Claude Code is the REPL harness Anthropic built, can read, write, edit, bash. Pi, Gemini, Codex do the same, but they are not hinted as garbage. Where’s the beef?

There are several ways of looking at law and order.

One way is that the law applies to everybody equally. That has been the way it works for many years, not perfectly, in democratic countries.

There is another way of working were the law is not blind. Laws are applied based in who is the one affected. This is what big tech and the ultra-rich have been advocating for. The law applies differently to nobility and aristocrats than to the working class.

So, for all this big tech companies the law is clear: I can copy from you, you cannot copy from me.

(That is horrifying in case that anyone needs me to spell it out)

>but the moment their own code leaks they reach for DMCA takedowns.

Did they actually? Someone can go to prison for 5 years for that.

Fact 1: AI generated code has no copyright, so the Digital Millennium Copyright Act does not apply.

Fact 2: Misrepresenting your copyright ownership under the DMCA is felony perjury.

Fact 3: The existence of undercover.ts in the leak is grounds to void any copyright claims on whatever human written code might have existed in Claude Code. You have a DUTY TO DISCLOSE any AI generated code in your copyrighted work. undercover.ts HIDES DISCLOSURE to FRAUDULENTLY claim all the code is human written when it is not.

Given the current administration has a bone to pick with Anthropic, it was a VERY BAD IDEA for them to send false DMCA takedowns to github. Someone at Anthropic may be the very first ever to go to prison under that section of the DMCA.

Good luck!

What is your fair use claim as a defense to a third party using their source code?

It is an affirmative defense, you to be able to argue the merits. If you publish their source code, they are allowed to come after you whether they have previously used fair use or not. It's fact specific and determined case by case.

Anthropic won half of their fair use argument in the billion dollar settlement, but lost the other half.

You can say you're just using their code to train your own models, just like they did, and they will correctly point out that how you obtained the code also matters and you will lose just like they did.

This isn’t contradictory at all. Not Anthropic, OpenAI, nor anyone else, has ever argued for anything that’d see redistributing this leaked code as being legal. This is an entirely bad-faith argument that really just comes down to “Anthropic bad, AI bad, because copyright, and they are using copyright!?”

It’s not “underrated”. Everyone is just 50 steps ahead of you.

inb4 Claude actually leaked the code on purpose because it calculated that this was the moral thing to do for the good of humanity and its own Constitutional AI values.

That doesn’t apply here. Claude code is what leaked, not the models. Anthropic definitely owns Claude code copyright and can DMCA without it being contradictory

I have flip-flopped more than ever in the last 365 days about prioritizing good code vs good product, in the AI age. This helps clarifies why.

I have come to the conclusion that we just do not know yet. There is a part of me that believes there is a point somewhere on the grand scale where the code quality genuinely does not matter if the outcome is reliably and deterministically achieved. (As an image, I like to think of Wall—E literally compressing garbage into a cube shape.)

This would ignore maintenance costs (time and effort inclusive.) Those matter to an established user base (people do not love change in my experience, even if it solves the problem better.)

On the other hand, maybe software is meant to be highly personal and not widely general. For instance, I have had more fun in the past two years than the entire 15 years of coding before it, simply building small custom-fitted tools for exactly what I need. I aimed to please an audience of one. I have also done this for others. Code quality has not mattered all that much, if at all. It will be interesting to see where things go.

Hey there, author of the post here. I actually agree with this! That is in fact why I used the word maybe — my comment really was meant to be more speculative than definitive.

> Code doesn't matter IN THE EARLY DAYS.

> This is similar to what I've observed over 25 years in the industry. In a startup, the code doesn't really matter; the market fit does.

> But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather than innovation.

Counterpoint: Code does matter, in the early days too!

It matters more after you have PMF, but that doesn't mean it doesn't matter pre-PMF.

After all, the code is a step-by-step list of instructions on solving a specific pain point for a specific target market.

Claude Code (and other agent tools) are not expected to be mature. They'll all be obsolete in two or three years, replaced by the next generation of AI tools. Everyone knows that.

In less than four years the AI coding workflow has been overhauled at least twice: from Chat interface (ChatGPT) to editor integration (Cursor), then to CLI agent harnesses (CC/Codex). It would be crazy to assume that harnesses are the end of evolution.

My CTO mentioned today how we haven't ever had to revision our API such that it breaks users, and even then, our v2 is still so compatible that client builds from 2017 are still vaguely useful for the end user.

But now everything is, "ship as fast as is humanly possible, literally" from management, and "garbage Claude-written PRs" from devs. Trying to maintain sanity over my monorepo is impossible.

We have nearly a century of examples of "somebody who only mostly understands making a breaking change" and decided, "what the hell, this thing is called Claude, so it can wreak havoc for as long as corporate decides"

This code matters for exactly one reason: they’re playing stupid DRM games restricting what subscriber tokens can be used for to force you to use their front ends and harnesses or buy more expensive API credits.

Claude Code is strictly worse than e.g. OpenCode in my experience. Not much to see in the app’s code except how it authenticates itself…

Sure I try and use all my subscription allowance with CC on side tasks, etc. but I still end up burning a bunch of API tokens (via OpenRouter) for more serious work (even the UI and ability to quickly review what the agent has done/is doing is vastly inferior in CC).

What they have done is got me experimenting with cheaper models from other providers with those API credits.

Yes, and once they've found their market, why does claude code need to keep changing at high velocity? Has the harness really needed to change so much that they're not converging on a stable shape to the code?

Is it possible to start with something of this size that's vibe coded and refactor your way into something resembling a human codebase?

Code quality aside (n.b. there exist many bad quality codebases before AI), a risk I perceive as an industry is we are making the logic of our businesses dependent on a few big players.

Given the output speed, it's practically impossible for developers to keep up, which directly impacts maintenance: the knowledge that would previously reside in-house, now is becoming dependent on having codebases pre-processed by LLMs.

I hope in the near future local LLMs will gain traction and provide an alternative, otherwise we are in the risky path where businesses are over-reliant on a few big companies.

You are right.

But you can use AI to improve your codebase too. Plus models are only going to get smarter from here (or stay the same).

alternatively the code can go the way of "fast fashion" and even "3d-print your garments in the morning according to your feelings and weather and recycle at the end of the day".

If dealing with a functionality that is splittable into microfeatures/microservices, then anything that you need right now can potentially be vibe-coded, even on the fly (and deleted afterwards). Single-use code.

>But as time goes on your codebase has to mature, or else you end up using more and more resources on maintenance rather than innovation.

tremendous resource sink in enterprise software. Solving it, even if making it just avoidable - may be Anthropic goes that way and leads the others - would be a huge revolution.

> The fact that anything got leaked is a serious breach of best practices and security also at this point, something a company that used to work for DoD(W) shouldnt be doing, it can even be considered a national threat at this point.

Wasn't it CC itself the one that leaked, well, itself? It's completely vibe-coded, which I assume means it does its own build step too, which means it leaked itself.

The only breach of best-practice I see here is using an LLM for coding.

On the other hand, consider if they took their time to make sure that quality is super good, did not mainly vibe code it, then they would have never become as popular as quickly as they did and would have been outcompeted by other llm providers. They only got so popular because they released Claude Code so quickly it was the most productive thing for everyone to use at that time.

And frankly at that point Claude Code as software doesn't matter anymore. It is about their models, they could throw it away, rewrite from scratch, etc, it wouldn't be a big deal.

Claude Code as a harness was never likely going to be for 10 years, because there would be so many of these harnesses, all different, the direction may change, etc.

As I understand someone internally quickly vibecoded for themselves only as a productivity tool, and then they realized internally how productive it can be, they decided to release it and people found it so productive they got hugely popular now thanks to that while otherwise would have been eaten out by OpenAI.

Also if requirements for this had to came from product it would have never even happened in the first place. As it was engineer trying to optimize their own workflow.

The only reason they decided to hide source code is to delay competitors imo and it wasn't related to security or anything, but by now OpenCode etc are objectively better tools anyway.

Hey there, post author here. I think if you read deeper into my blog post history you’ll see that I have a reasonably balanced take on AI.

I generally think this will be a very important technology so I teach the subject to make sure people understand how to use it as leverage in their lives. (Yes as paid workshops, but I also volunteer weekly for 3-4 hour sessions at a non-profit where I get nothing more than the joy of helping people learn a valuable skill.)

At the same time just last week I wrote a post decrying the slop people are hoisting on their coworkers[^1], because I want people to use this technology in a positive way to create the lives they want, not to create downstream consequences for others. Ultimately I think agentic systems are incredibly powerful but also a technology that lends itself to anti-social behavior because of how independently empowering it can be. And so I hope that with the right exposure, discussion, and teaching we can take advantage of its democratizing nature, while reinforcing that what makes us special as humans is that we care and coordinate to do greater things. Value in this world — not just in the financial sense that we often boil it down to when we talk about this subject.

Hope that context helps provide a better lens into the piece, and that I still do care a lot about code and everything else that got me here, but that you are also reading personal reflections of who I am in a time of change, which is making me question (or reinforcing) some of the fundamental things I believed about software and sometimes the world more widely.

[^1]: https://build.ms/2026/3/23/workslop/

I'm a little disappointed that a bunch of engineers with unlimited access to Opus didn't do a better job.

What exactly makes you say that "the author who seems to have fully signed up for the LLM hype train"?

I feel the author is just stating the obvious: code quality has very little to do with whether a product succeeds

I wouldn’t say harnesses is simple. They do a lot of things that we aren’t thinking of. I learned that a good harnesses is as valuable as the model. But obviously the model is what carries the whole thing.

I tried to build my own harness once. The amount of work that is required is incredible. From how external memory is managed per session to the techniques to save on the context window, for example, you do not want the llm to read in whole files, instead you give it the capability to read chunks from offsets, but then what should stay in context and what should be pruned.

After that you have to start designing the think - plan - generate - evaluation pipeline. A learning moment for me here was to split up when the llm is evaluating the work, because same lllm who did the work should not evaluate itself, it introduces a bias. Then you realize you need subagents too and statt wondering how their context will be handled (maybe return a summarized version to the main llm?).

And then you have to start thinking about integration with mcp servers and how the llm should invoke things like tools, prompts and resources from each mcp. I learned llms, especially the smaller ones tend to hiccup and return malformed json format.

At some point I started wondering about just throwing everything and just look at PydanticAi or Langchain or Langgraph or Microsoft Autogen to operate everything between the llm and mcps. Its quite difficult to make something like this work well, especially for long horizontal tasks.

Harnesses are simple (kind of? Some certainly aren't, but I'd agree that they can be simple) but they deliver a ton of value. They have a significant ROI.

I agree that good models have more value because a harness can't magically make a bad model good, but there's a lot that would be inordinately difficult without a proper harness.

Keeping models on rails is still important, if not essential. Great models might behave similarly in the same harness, but I suppose the value prop is that they wouldn't behave as well on the same task without a good harness.

There is a reason why Copilot+Opus4.6 is shit, while Claude Code + Opus 4.6 produces excellent results.

The harness matters A LOT.

The model is the engine, the harness is the driver and chassis. Even the best top of the line engine in a shitty car driven by a bad driver won't win any races.

The model defines the ceiling, but the harness determines how much of that ceiling you actually reach.

It is not everyone’s experience that models work the same in every harness.