This really connect with the latest conversations I had with coworkers regarding how can we review gigantic PR generated by AI. One way could be to ask the submitter to give their prompt as part of their contribution. This way it's easier for the reviewer to understand what was the thought process of the contributor and if this very process is sound. Not saying that this way to review is a silver bullet, but at least it removes some weight.

I heard about one project where people are trying to only commit really thorough specifications and integration tests to a repository. Then a CI triggers an agent sandbox which generates all the product at once. This approach is highly debatable because really token consuming but is fairly interesting because the project ends up to be really well documented and tested.

However, having a rigorous spec process which ends up giving lots of details to the agent seems to me the right way to build stuff with LLMs. Rather than iterating and piling changes after changes.

I also think that might not be everything you need to really vet/recreate those PRs since there's a lot of strategic and operational stuff that goes into the pre-composition runs (sometimes I actually throw everything away and restart), so something a little more sophisticated would be interesting.

Obviously highly dependant on the complexity of the app.

Small CLI tools or helper react apps you'll throw away? Yes, I'll do PRs from one shots.

I had a recent case where I, being the lead, sliced up the work real good into an epic and what not and a guy on the team just did a "hurr durr, Claude, go wild with all that" and threw a huge PR over the wall linked to 5+ stories.

Well, we got to have "the conversation" after that and learned how to fix these kinds of PRs together...

Claude absolutely loves to reimplement the wheel locally instead of just calling a method in a library we already depend on. Every doc comment and README.md update is bloated by 2-5x what's needed to communicate intent or to actually be read by a human later. It makes random drive-by edits that aren't necessary and weren't asked for in the prompt. It's a well oiled machine for producing astronomical bloat by default if you don't supervise and rein it in!

The discipline of splitting them up helps in almost every dimension.

What are the PRs you're thinking of?

You're welcome to do large PRs, I'm not a fan of huge PRs though and would not pretend to review them (as pretending is what it would be), nor would I like to work somewhere where this is the culture.

To add to my openspec shilling above, I've been known to "fix" large PRs by reverse engineering specs from them and building each spec out in a separate PR.

Last week me and a coworker turned a 15k line PR into 10 x 1.5k line ones that went in smoothly.

1. PRs come with "the prompt". In openspec parlance this is a set of docs: a proposal, design, specs, task list. 2. I have a tiny skill to slice and dice PRs, so I can review each part of the system separately by rewriting commits in order of reviewal: specs/docs, production code, tests, evidence. I sometimes pull DB queries to a separate commit for focused review. 3. The evidence bit is built by another skill: go over all added spec scenarios and produce a markdown document with links to the code implementing the scenario and the tests proving the implementation works. Emacs helps me jump back and forth via those links and read the parts I'm interested in.

My next goal is to extend openspec schemas with custom workflow steps to make PRs land in my preferred review structure and contain the evidence report, so I don't have to build it.

I'd say the cost actually grows as people get laid off left and right, and on top of that, a 1000 line PR from a good human, give me a case of beer and I'll make me some sense of it, but if it's AI slop, get ready to hand me a crate of homemade Slivo or I won't touch that...

This sounds like slop. Like an engagement bait. Also a no slop manifesto should start by defining “slop” as the first thing. That’s not something for the comment section.

> AI cannot replace human judgement, it can only amplify our judgement (or lack thereof)

Why not? Did you mean should not.

Oh no, the horror

The comparison doesn’t work for the music industry, at least. Many hit songs are written and produced on a whim, while people analyze it for years.

I think the problem with those Maths proofs was they were massively rushed and OpenAI just couldn't be bothered to do it properly or actually check them. They were more interested in the PR than in helping advance Mathematics.

It sounds to me like you're arguing against this point in particular.

More power to you. I'd like never to work at a place that sanctions slop-validated-slop.

If you find your agent sucks at programming and has zero taste for good design, then that's arguably a 10x of the operator.

I'm quite pleased with the quality of programming and design that I'm able to achieve with the processes I do with agents.

I've certainly noticed that when I watch a junior use AI they've produced nothing but the most intolerable slop man has ever seen. And I've seen principles and architects produce one shots that are such shining examples of quality engineering that they remain nothing more than goals to me.

Most of them exited this industry before their career was over.

Good luck to you

What does alpha mean in this case? I only understand this term in from a finance perspective (excess returns). Is it used here to mean 'value'? E.g. there is always value in reviewing something?

So true, I feel guilty not fighting it at the place I work at, but it seems impossible.

This manifesto gives me a spark on hope I haven't felt in months.

From my own personal experience, which may not reflect the broader industry although I suspect it does, the ones who embrace slopping with the least regard for their peers are also the ones perceived as the most effective by their employers. Those who take a principled stance get the worst of both worlds. They cannot combat the deluge of slop with their own clanker, and they lose the influence with their company leadership that would provide sponsorship to change how AI is being used. This creates competitive pressure to follow suit, and from there it is a race to the bottom.

That's a very big "if". So far, it appears that AI slop leads to worse business outcomes.

It's arguably the most successful piece of software in the past decade.

It took a software company from a 10 billion company to a 1.5 trillion company in about one year.

This is the counter example to you. With AI, a small team can make a trillion dollar business in the order of days.

Hard to care about developers crying about the usability of their Dev tools when their businesses are 100Xing and 1000Xing per year on the back of AI code

And you have no idea if the Microsoft outage was caused by AI. You are just lazily attributing an issue to AI because it's convenient for your argument which is a very ignorant tactic

More than 20 apps developed in the last six months, all top quality, I haven't coded a single line, speed and output is what matters, results improving by the day and will be unrecognizable in a couple of years by any metric

AI is unstoppable and no matter how many manifests luddites write AI won't care

It really boggles my mind. I mean, come on just reuse the curriculum from the past 20 years. You do have that don’t you? Don’t you?!

> What shipped, who's using it, and how it's helping them matters FAR MORE than lines of code, prs merged, tokens spent, or the number of agents running in parallel.

Sometimes when I hear shocking amounts of money spent on AI tokens, I wonder if someone's obsessing over the tech and forgetting that only the result matters.

Slop is when we put less effort into producing something than we ask the consumer to spend understanding it.

If you are focusing on quality, AI should make things slower, not faster, on that you still do the same work you normally do by hand, but in addition do that, you use AI to make it better. For programming it could mean you still write the code by hand, but you make an additional pass with a LLM to find bugs you could have missed.

... and it will save time in the future, sometimes, slow is fast.

I'm getting excellent code reviews with copilot; it really thinks through corner cases that would take a very long time to discover. It's also very easy to use with no learning curve.

But keep in mind that AI, like most technologies, is a "labor saving device," where the point is to lower the effort needed to create something. I'm often doing 2-4 days worth of work in 2-4 hours. Most of the time savings come from work that I understand and would produce similar results.

(Rejecting a labor saving device like this is foolish.)

It leaves me two options: do most of the work myself as to avoid AI stupidity, then have the AI help me with the corner cases it is so good at finding. It takes time but the final quality is better.

Or let the AI do its thing. The end result is usually worse than if I did it by hand but it is fast. I.e. slop. Sometimes, slop is fine: a one off script, a personal project,....

When you put it like that, seems the problem is on the human side

Industry: "What makes you think software not sucking is part of our equation?"

There is a lot of value in the fact that none engineers can build products now! Should AI products adhere to a certain quality standards? Yes! Should they be treated similarly as "human created" ones... Well, yes. Like it or hate it.

And this is something that has always happened. Way earlier than current AIs we had already coined the term "shovelware" that was mostly a large quantity of sloppy software. We also had plenty of sloppy drawings at sites like DeviantArt. AI just made it way easier for slop to happen, but the ones producing slop are always people.

If it was cheaper and easier to make shovelware before, it is 10,000x cheaper and easier now.

A major reason slop exists is because they are not "better" at coding, given some subjective criteria. They are notably worse at documentation and somewhat poor at choosing abstractions in my experience. For the most part, I witness the tools copying other examples out of the working repository, which makes them exactly as bad as the humans who originally wrote the code.

> will always code at a lower level with the time passes

For humans, this is traditionally an anti-pattern. We are good at intuiting abstractions and knowing when to use them or climb up and down the abstraction hierarchy. For LLMs, this is also an anti-pattern, because going lower-level is an exponential waste of tokens; both for writing and reading the resulting code, which they do constantly in order to understand the project again and again in order to fulfill your prompts.

Thinking of human review as a "bottleneck" is incorrect framing. We are quality control. You can choose to cede quality control to LLMs and agent harnesses, that's up to you. In my experience this generally leads to a meteoric rise in slop, because the tools increasingly resort to writing more code to solve a problem instead of updating existing code or writing the correct code. When I shake my head at some slop code, then read the slop comment that uses some slop justification that isn't real and only existed in the prompt context, I am happy that I took the time to review it. Maybe that makes me a bottleneck, oh well.

I think if you see real examples you can better understand what I mean

Faster definitely, but even with the latest Fable model "better" is often debatable and varies a lot based on what you care about. I can often rewrite what Claude did in 1/2 the lines or less to do the same thing while making it easier for humans to understand and maintain. Claude gives me a sculpture in a good rough starting shape, but it usually needs to be sculpted down at the end whether manually or by prompting Claude about the unnecessary bloat it generated.

> Claude gives me a sculpture in a good rough starting shape, but it usually needs to be sculpted down at the end whether manually

I make the sculpture in a good starting shape manually by writing the code that matters, data shaping, interfaces etc. It's then way more effective filling the rest following the path I created. Way better than any spec driven, as code is the ultimate spec.

The other way around makes it harder for me to fix, cause even with a lot of steering it makes things in a way i'd never introducing a bias that requires a high discipline and energy to fight back

--------

We are uncovering better ways of developing systems by using AI and guiding others to use it responsibly.

Through this work we have come to value:

    Human accountability over delivery velocity
    Human dignity and control over unsupervised autonomous execution
    Human augmentation over replacement
    Impactful outcomes over raw code generation
    Human collaboration over individual uplift

For example -

You make more money if you deliver quickly than you do if you have "accountability." What even is accountability, how do I explain it to a CEO? Is this office speak for blame? Is the idea to know who to yell at so you can feel better, or to make money? Feelings don't sell widgets.

"Human dignity and control" - Who is this valuable to? Not consumers, they want Walmart prices. Not companies, they want Walmart profits. What's in it for them?

I disagree. Nothing you said is wrong, really, but like most good things in society change requires cooperation. To get that you have to consider other peoples perspectives. Language is for communication. So what are we trying to communicate and how do we do it effectively?

First decide who it is you're trying to convince, and then target the message that they need to hear. Don't lie, just choose the most compelling argument for that audience. People have a finite amount of attention and won't sit through a lecture that's clearly not meant for their ears.

For example, we might rephrase it in terms of reliability when talking to engineers, or into the business advantages of being able to introduce new features faster when humans understand the codebase for an executive. Just figure out who it is that needs convincing the most, and explain to them why it benefits them.

Right now this is just rabble rousing. It feels like the goal is to convince those who are already angry that they should be even angrier. To what purpose though? Everyone is angry, and the world doesn't need more. What it needs is to channel that anger into something useful or, more productively, to start helping to convince those who aren't already.

If you do not value human dignity, naturally none of this matters. I do not judge people who need Walmart prices, I judge people who prefer they have more regardless of what that does to others. Companies simply need boundaries, that's what the government is for, defense of the common good in the face of people pursuing their individual ones.

Selling it is good, but the point is to be able to articulate it to yourself before you package it up in various forms for others.

Will "No AI[1] slop, aim for understanding system we ship in human brains instead" be advantageous in capitalism? I sincerely doubt it. And that makes me sad.

[1]: Or, to prevent slop: at least, no speed-up beyond catching up to what was still well-thought out in terms of input and/or reviewed by humans. AI can still be a tool, but must never take all roles in a process from gradle to grave.

AI has really disrupted that, and I’m thrilled to see folks trying to bring back the best parts of it (namely shared understanding and contribution). But I agree with others, making the movement anti slop feels the wrong way around. What it’s getting at IMO is deep understanding and shared understanding are crucial to human progress, and reckless AI use compromises that

Is getting the same output as everyone else bad? I'd say not necessarily. When you're making something, you might want to spend your "innovation tokens" on the core of what you want to do better. Then do a good-enough job at everything else.

To me it feels like the subtext in this is that making things more accessible is bad because then your stuff isn't unique anymore? I do not think this zero-sum / scarcity mindset is really accurate or helpful, IMO.

Should have taken their own advice and reduced this to five points max. This is too verbose and redundant.

I’d suggest you bake it into that header line on writtten by; something like this (but edited depending how ai was used):

“Written without AI assistance by the speakers and attendees of AIE Code Summit 2026”