--- title: No AI Slop: A Manifesto | daily.dev description: A group of AI Engineer Code Summit speakers and attendees published the 'No AI Slop' manifesto, a successor in spirit to the 2001 Agile Manifesto. It defines... canonical: https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: No AI Slop: A Manifesto | daily.dev og:description: A group of AI Engineer Code Summit speakers and attendees published the 'No AI Slop' manifesto, a successor in spirit to the 2001 Agile Manifesto. It defines... og:url: https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz og:image: https://api.daily.dev/og/posts/WZbSqXsTZ.png og:image:alt: No AI Slop: A Manifesto og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # No AI Slop: A Manifesto **[Hacker News](https://daily.dev/sources/hn)** · 6 min read · 1 upvotes · 0 comments ## Summary A group of AI Engineer Code Summit speakers and attendees published the 'No AI Slop' manifesto, a successor in spirit to the 2001 Agile Manifesto. It defines slop as putting less effort into producing something than you ask the reader to spend understanding it. Using AI isn't itself slop; slop happens when people pass along AI output without taking responsibility for its quality. The signers resolve to keep doing their own thinking before work starts, disclose when an agent wrote something being sent, and review at least some subset of AI output depending on the stakes. They also note that one-shot prompts and vibe coding aren't automatically bad if they still produce a useful, maintainable outcome. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does 'AI slop' mean in the context of software engineering? AI slop is when someone puts less effort into producing something, such as code, a doc, or a message, than they ask the person consuming it to spend understanding it. Using AI isn't inherently slop; it becomes slop specifically when AI output gets passed along without the sender taking responsibility for its quality or the reader's experience. _Developers figuring out where to draw the line on AI-assisted work can follow this debate on daily.dev._ ### Should I review every line of AI-generated code before shipping it? Not necessarily; one-shot prompts and vibe coding are considered high-leverage tools that aren't automatically bad, as long as they don't undermine the outcome, like a useful product or a maintainable system. Agent reviews, linters, and verifiers help but aren't sufficient alone; some subset of outputs should still be reviewed by a human, with the subset depending on the stakes involved. _Teams setting their own AI code review standards can track this ongoing discussion on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 110 comments across hackernews (as of 2026-11-14). **TL;DR:** Discussion is split between practical debate on how to review AI-generated PRs at scale and broader skepticism about whether a manifesto like this can counteract business incentives that reward fast, unreviewed AI output. **Sentiment:** 25% positive · 40% mixed · 35% skeptical **The case for** - Some see value in the framing that slop is defined by effort asymmetry between producer and reviewer, calling it a balanced take worth signing. - Several propose concrete mitigations like requiring prompts/specs alongside PRs or using tools (e.g. openspec) to slice large AI-generated PRs into reviewable chunks. - Some find hope in the manifesto as a counterpoint to feeling pressured to accept unreviewed AI slop at work. **The pushback** - Many argue the core incentives of capitalism/business reward speed over accountability, so the manifesto likely won't gain traction the way Agile did. - Commenters note human review doesn't scale against the volume of code agents can produce, making review itself the bottleneck. - Some find the manifesto's own prose ironic—verbose, vague, or 'engagement bait'-like, undermining its anti-slop message. - Disagreement over whether reviewing prompts/conversation history actually validates correctness of the resulting code. - Some reject the framing entirely, arguing AI agents will replace human-centric review workflows regardless of manifestos. **By community** - hackernews (mixed): A long, multi-threaded debate mixing practical PR-review tactics, skepticism about the manifesto's business viability, and pushback on its own wordy execution. **Hottest debate:** Whether large AI-generated PRs should simply be banned/split up, versus cases where big, sweeping AI-assisted rewrites are seen as legitimate and effective. **Open questions** - How should teams practically review AI-generated PRs or prompt/conversation history at scale without the review itself becoming unwieldy? - Will market and business incentives actually reward the manifesto's values of accountability and review, or will speed continue to win out? - Is 'alpha' in reviewing truly durable, or will agent-to-agent workflows eventually replace human review entirely? **Highlights** > > Slop is when we put less effort into producing something than we ask the consumer to spend understanding it. This feels directionally right, but if you define slop this way then you put a cap on AI productivity. For example, I heard an interview with Terry Tao talking about how the work of mathematicians is now to understand the proofs generated by AI. He's, by definition, describing these groundbreaking proofs as slop (by the above definition). > — [seizethecheese on hackernews · 5 comments](https://news.ycombinator.com/item?id=50489508) > While I am sympathetic to the authors, the reason that agile swept over the industry is that it was a demonstrably more effective when measured by business outcomes. "AI slop all the things" is miserable for human employees and introduces new kinds of dysfunctions called out or hinted at in this manifesto. However, if on balance it is more effective when measured by business outcomes, there is little chance of this manifesto gaining traction in the industry. 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. > — [lemarchr on hackernews · 1 comments](https://news.ycombinator.com/item?id=50489675) > The manifesto circles around a central idea that it never fully identifies: whether AI is involved or not, all slop is made by HUMANS. Because the real cause of "slop" is that someone didn't care and published the first result they got, as if it was the final product. They didn't put in the effort to analyze what they got, improve on it and deliver a minimum quality. 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. > — [carra on hackernews](https://news.ycombinator.com/item?id=50490837) > The problem is that the things on the left are legitimately less valuable than the things on the right to most people. The target audience will eat it up, but why should anyone who isn't a developer care? This entire thing fails to explain it's value to anyone who isn't already convinced. 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'm not saying I disagree, I'm saying this isn't how you sell it. > — [mapontosevenths on hackernews](https://news.ycombinator.com/item?id=50493421) > > Because LLMs continue to be better at coding 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. > — [tadfisher on hackernews · 1 comments](https://news.ycombinator.com/item?id=50491075) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50488769) · 170 points · 110 comments ## Similar posts on daily.dev - [When AI content isn't slop](https://daily.dev/posts/when-ai-content-isn-t-slop-3asgsozxp) · Planet Python · 0 upvotes · 0 comments - [AI Slop is Killing Online Communities](https://daily.dev/posts/ai-slop-is-killing-online-communities-49ntj9vsm) · Lobsters · 2 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#vibe-coding](https://daily.dev/tags/vibe-coding), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"No AI Slop: A Manifesto","url":"https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz"},"datePublished":"2026-11-13T21:24:43.729Z","dateModified":"2026-11-13T22:51:03.967Z","description":"A group of AI Engineer Code Summit speakers and attendees published the 'No AI Slop' manifesto, a successor in spirit to the 2001 Agile Manifesto. It defines...","image":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","thumbnailUrl":"https://media.daily.dev/image/upload/s--0_ODbtD2--/f_auto/v1722860399/public/Placeholder%2008","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,vibe-coding,code-review","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"No AI Slop: A Manifesto"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/no-ai-slop-a-manifesto-wzbsqxstz#faq","mainEntity":[{"@type":"Question","name":"What does 'AI slop' mean in the context of software engineering?","acceptedAnswer":{"@type":"Answer","text":"AI slop is when someone puts less effort into producing something, such as code, a doc, or a message, than they ask the person consuming it to spend understanding it. Using AI isn't inherently slop; it becomes slop specifically when AI output gets passed along without the sender taking responsibility for its quality or the reader's experience. Developers figuring out where to draw the line on AI-assisted work can follow this debate on daily.dev."}},{"@type":"Question","name":"Should I review every line of AI-generated code before shipping it?","acceptedAnswer":{"@type":"Answer","text":"Not necessarily; one-shot prompts and vibe coding are considered high-leverage tools that aren't automatically bad, as long as they don't undermine the outcome, like a useful product or a maintainable system. Agent reviews, linters, and verifiers help but aren't sufficient alone; some subset of outputs should still be reviewed by a human, with the subset depending on the stakes involved. Teams setting their own AI code review standards can track this ongoing discussion on daily.dev."}}]} ```