--- title: The Four Horsemen of Agentic Coding | daily.dev description: An opinion piece argues that agentic coding, despite its usefulness, carries four interrelated harms: code slop (LLM output has a distinctive, repulsive... canonical: https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Four Horsemen of Agentic Coding | daily.dev og:description: An opinion piece argues that agentic coding, despite its usefulness, carries four interrelated harms: code slop (LLM output has a distinctive, repulsive... og:url: https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd og:image: https://api.daily.dev/og/posts/cgNq3K7Jd.png og:image:alt: The Four Horsemen of Agentic Coding 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. # The Four Horsemen of Agentic Coding **[Lobsters](https://daily.dev/sources/lobsters)** · 7 min read · 0 upvotes · 0 comments ## Summary An opinion piece argues that agentic coding, despite its usefulness, carries four interrelated harms: code slop (LLM output has a distinctive, repulsive quality that discourages humans from engaging with codebases), alienation (engineers lose a sense of ownership and care because they no longer write code by hand), deskilling (reliance on AI erodes existing skills and removes incentives to learn, with little learning curve to compensate), and team fallout (interpersonal communication and skill-based identity within teams erode as engineers increasingly talk to agents instead of each other). The author offers no solutions, framing these as unresolved costs of AI-assisted development. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community take How the wider developer community reacted, aggregated from 2 discussions and 177 comments across lobsters, hackernews (as of 2026-10-03). **TL;DR:** Reactions split between people who find the essay's four harms (slop, alienation, deskilling, team fallout) painfully accurate from lived experience, and others who argue the slop/skill problems are overstated or model-dependent and that good process can avoid them. **Sentiment:** 20% positive · 35% mixed · 45% skeptical **The case for** - Several describe concrete workflows (checked-in plan files, reviewing every commit, limiting agents to a pairing role) that keep quality and ownership intact. - Some report thriving, collaborative teams using agents heavily without losing camaraderie or code quality. - A few argue the speed and capability gains are so large that the four harms are an easily justified tradeoff. **The pushback** - Many describe real erosion of team communication, with Slack channels going quiet and colleagues passing along raw LLM output instead of engaging directly. - Code review fatigue and a flood of low-quality AI-generated PRs were cited as a growing burden, especially from less experienced engineers. - Some feel accountability is being outsourced to AI as a convenient scapegoat when bugs or mistakes occur. - Deskilling and loss of architectural/codebase nuance were flagged as real risks, especially in large, long-lived codebases. **By community** - lobsters (mixed): Commenters mostly share personal workflows for taming agentic coding and swap practical mitigations rather than arguing over whether the harms are real. - hackernews (heated): A large, contentious thread with strong disagreement over whether 'slop' is still a real problem, whether caring about craft versus shipping fast is a false dichotomy, and whether teams are actually losing cohesion. **Hottest debate:** Whether resistance to agentic coding reflects genuine craft/communication losses or is really just a divide between people who 'love problem-solving' versus those who saw coding as 'just a job'. **Open questions** - Can companies actually enforce practices (like AI-free days or mandatory code review standards) that preserve skills and team cohesion without sacrificing the productivity gains? - Is the perceived decline in team communication a direct effect of agentic coding, or does it reflect pre-existing weak team culture being exposed? - How much of the 'slop' complaint is really about outdated models versus an inherent property of LLM-generated code? **Highlights** > My work Slack channels are ghost-towns. People are logged in, but they're never saying anything. I often find myself wondering if anyone is even working. PRs have their names on them, even the review comments are posted from _their_ accounts, but it is obvious that Claude wrote everything from the code, the unnecessarily verbose change summary, to their comments. Even their replies to my change requests start with "You're right — …". I miss the days when the engineering Slack channels had long threads of new and interesting ways to do things, discussions of something we could do next to make work easier or fix long-standing issues. We used to build up our own knowledge of who was good at specific things, what they'd be interested in working on. Now everyone just has their slop-machine spit out every piece of a change for the entire stack without paying any attention to the details. > — [paularmstrong on hackernews · 2 comments](https://news.ycombinator.com/item?id=49935303) > There's a particular sting to being passed raw, unfiltered output from the LLM hose. I think you're onto something with the mismatch in expectations (I was expecting a conversation that led to insights we might both share, and the other party was expecting to answer a question quickly without much thought). I think there's something deeper than that, too. Almost a feeling of betrayal? I cared in part because I thought everyone else cared, too, like we were working towards a common goal. Asking a question in search of shared understanding only to be passed the modern equivalent of a LMGTFY link hurts in a very particular way. I thought they cared about this, too, but they're only trying to get the bag. I get it, times are difficult right now, but it doesn't make it hurt less. > — [intrikate on hackernews · 2 comments](https://news.ycombinator.com/item?id=49936271) > I feel like I'm living in an alternate universe - my company has fully adopted agentic coding, we're working with: - large codebases - business critical software for clients that don't tolerate downtime - agentic and classical features We still collaborate well, we still care about quality, we still have good knowledge of the codebase, but I haven't written a single line of code myself in over a year. We have not had a single incident that I'm aware of where we shipped a slop and it created downtime. We're building a "software factory" that is currently handling low-level chore tickets and merging about 1/3rd of our PRs. A year from now I imagine it will be doing significantly more, and I don't think anyone is going to get fired because of it (if anything we'll keep hiring more). I don't see this as an either/or thing. If there is some hidden ocean of slop that we're bound to fall into I don't see it anywhere. Where is the disparity? > — [headcanon on hackernews · 1 comments](https://news.ycombinator.com/item?id=49938007) > The backlash against agentic coding comes from the split that has already existed among professional software engineers. The ones who are most resistant to it are the ones for whom it has been "just a job", but the ones who love it are the ones who love solving problems. It's now possible for a small team (one person, a few) to solve truly daunting software problems with the help of agentic methods. If you were a 9 to 5er who valued craft but didn't dream about solving problems, AI is a buzz kill. > — [resters on hackernews · 6 comments](https://news.ycombinator.com/item?id=49935783) > The real problem of this horsemen is that there is no incentive to fix them by the big players, because it is not something companies are interested in > — [gbalduzzi on lobsters · 1 points](https://lobste.rs/s/wevegu/four_horsemen_agentic_coding#c_csl2y2) **Source threads** - [lobsters](https://lobste.rs/s/wevegu/four_horsemen_agentic_coding) · 51 points · 11 comments - [hackernews](https://news.ycombinator.com/item?id=49934511) · 104 points · 166 comments ## Similar posts on daily.dev - [Agentic Coding Is a Trap](https://daily.dev/posts/agentic-coding-is-a-trap-hanolpuva) · Khalil Stemmler · 3 upvotes · 0 comments - [Agents are ushering in the Antisocial Coding era](https://daily.dev/posts/agents-are-ushering-in-the-antisocial-coding-era-lhci5kb0c) · Justin Searls · 0 upvotes · 0 comments - [When Agentic Coding Goes Off the Rails](https://daily.dev/posts/when-agentic-coding-goes-off-the-rails-901po5tdi) · RUBYLAND · 0 upvotes · 0 comments - [Pity the developers who resist agentic coding](https://daily.dev/posts/pity-the-developers-who-resist-agentic-coding-hro9to6ro) · InfoWorld · 0 upvotes · 0 comments - [I Miss Writing Code](https://daily.dev/posts/i-miss-writing-code-yxc7ryasd) · iamluminousmen · 0 upvotes · 1 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#company-culture](https://daily.dev/tags/company-culture) [View this post on daily.dev](https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd) ```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":"The Four Horsemen of Agentic Coding","url":"https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd"},"datePublished":"2026-10-02T23:23:18.120Z","dateModified":"2026-10-03T15:54:02.510Z","description":"An opinion piece argues that agentic coding, despite its usefulness, carries four interrelated harms: code slop (LLM output has a distinctive, repulsive...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9f7e8cb8b1817c7336c4b60958195896?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9f7e8cb8b1817c7336c4b60958195896?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Lobsters","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":"Lobsters","logo":"https://media.daily.dev/image/upload/s--tl8v_Fku--/f_auto,t_logo/v1698841318/logos/lobste.jpg","url":"https://daily.dev/sources/lobsters"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-four-horsemen-of-agentic-coding-cgnq3k7jd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,company-culture","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Lobsters","item":"https://daily.dev/sources/lobsters"},{"@type":"ListItem","position":3,"name":"The Four Horsemen of Agentic Coding"}]} ```