--- title: The Mythical Man-Month in the Age of AI | daily.dev description: Brooks's Law still holds when you swap people for AI agents, the author suggests, but it mutates rather than vanishing. Brooks's 1975 claim, 'adding manpower... canonical: https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Mythical Man-Month in the Age of AI | daily.dev og:description: Brooks's Law still holds when you swap people for AI agents, the author suggests, but it mutates rather than vanishing. Brooks's 1975 claim, 'adding manpower... og:url: https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs og:image: https://api.daily.dev/og/posts/IaSWxpnHS.png og:image:alt: The Mythical Man-Month in the Age of AI 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 Mythical Man-Month in the Age of AI **[Hacker News](https://daily.dev/sources/hn)** · 2 min read · 0 upvotes · 0 comments ## Summary Brooks's Law still holds when you swap people for AI agents, the author suggests, but it mutates rather than vanishing. Brooks's 1975 claim, 'adding manpower to a late software project makes it later', still applies in changed form. Nine agents still can't deliver a baby in one month: sequential tasks stay sequential. Overhead shifts from managing people to managing agents, since someone still has to define 'done', review code, and catch hallucinations. The author proposes a 2026 update: 'adding agents to a project with unclear requirements gets you the wrong answer faster'. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does Brooks's Law still apply when you use AI coding agents instead of adding more developers? Yes, it still applies but in mutated form. Sequential tasks remain sequential, so nine AI agents cannot finish a task faster than one agent working through it step by step, just as nine people cannot deliver a baby in one month. The overhead shifts from managing people to managing agents, including defining 'done', reviewing output, and catching hallucinations. _Anyone orchestrating multiple coding agents can track this kind of thinking on AI-assisted development on daily.dev._ ### What happens when you assign many autonomous AI agents to the same codebase without clear requirements? Without clear orchestration, multiple autonomous agents working on a single codebase will rewrite each other's work in a high-speed loop. The proposed update to Brooks's Law captures the risk: adding agents to a project with unclear requirements gets you the wrong answer faster rather than a working solution sooner. _Teams scaling multi-agent coding setups follow lessons like this on daily.dev before hitting the same mess._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 135 comments across hackernews (as of 2026-10-27). **TL;DR:** Commenters broadly agree Brooks's Law still applies but debate shifts to whether fast, cheap AI-generated prototypes are a good substitute for upfront requirements gathering versus a trap that lets people skip critical thinking; many also argue multiple agents create coordination and review overhead similar to human teams. **Sentiment:** 30% positive · 45% mixed · 25% skeptical **The case for** - Fast, cheap AI-generated prototypes can be more useful than abstract requirements meetings for surfacing what stakeholders actually want. - Some report successfully using agents for grunt work, bug triage, and reverse-engineering with large productivity gains. - A few describe running many agents/projects in parallel as genuinely more throughput, if mentally taxing. **The pushback** - Relying on quick wrong answers risks shipping a shoddy prototype as if it were the real thing, or anchoring stakeholders to a flawed first draft. - Verification and review of AI output doesn't scale as fast as generation, so quality and understanding can silently degrade. - Running multiple agents in parallel often just recreates human coordination overhead (agents stepping on each other, noisy tests, excessive back-and-forth with subagents). - Several argue AI is weak at architecture, judgment, and figuring out what to build versus just producing code. - Outsourcing thinking to agents can erode engineers' own reasoning skills and mental model of the codebase over time. **By community** - hackernews (mixed): Discussion splits between enthusiasm for rapid AI-driven prototyping as a requirements tool and skepticism that it just produces fast, confident wrong answers or outsourced thinking. **Hottest debate:** Whether a fast, cheap, flawed AI-generated prototype is a legitimate substitute for careful requirements gathering, or a trap that leads teams confidently down the wrong path. **Open questions** - How do you reliably tell a 'wrong answer fast' from a genuinely workable solution when verification itself is expensive or slow? - Does working with multiple agents in parallel actually save time, or does it just relocate the coordination overhead Brooks described? - Is there a sustainable way to keep developers' critical thinking and codebase understanding sharp when agents do most of the writing and reviewing? **Highlights** > Not if you turn off your brain. Never actually stop to question the path you're going down, because the speed is making you blind. Which is what I feel I see more and more. Or how do you even know it's the wrong answer if you didn't think it through before starting? One example: setting the agent ablaze on some task, keeping it going, and after a few days of working with the agent you have a feature. But it's not what you were supposed to make. The agent didn't have all the context and made something slightly off, and you never internalized the problem enough to even spot it. If you actually stopped to think a bit on how the feature would have to work to tie it in with everything else, like you would have done before, you would've spotted it. Second example: something wasn't feasible to do before, due to not being worth the time investment. Like a feature that would need a bigger architectural change to implement. You and the agent take a crack at it, and rewrite huge parts of the code, and it seems to work. But now no one understands how, and it might have been the wrong way to solve it, you just went with it. Before, you would've sat down and discussed and thought about the architectural tradeoffs. Now one decision was just made with little thought. > — [matsemann on hackernews · 4 comments](https://news.ycombinator.com/item?id=50256072) > What's easier to use as inspiration for coming up with a list of requirements?: 1. A blank sheet of paper 2. A one-shotted POC in the span of an hour with $4 of tokens that is clearly wrong in 20 different ways? > — [Fordec on hackernews · 10 comments](https://news.ycombinator.com/item?id=50255812) > Sequential tasks are still sequential. The difference is one engineer can you work on many sequential tasks in parallel. The old way of working where an engineer picks up a ticket and works it through to completion before working on the next one is over. Engineers in my team work on about 5 at a time, sometimes far more. That might mean working on multiple features at once, or working on CI or DX or tooling improvements or bug fixes while building a feature, but the days of working on one thing at a time are well and truly over Context size and ability to context switch without burnout is what will differentiate a median engineer from a great engineer, not technical ability > — [s08148692 on hackernews · 3 comments](https://news.ycombinator.com/item?id=50257141) > I agree with both you and matsemann. Getting the requirements right by conducting a cheap POC is a good approach. Matsemann is highlighting the failure that creeps in when the POC is shipped as if it meets the requirements. Someone has to sign off on the requirements and also what is released. So, two approval steps by a person. The first approval is for a plan and the acceptance criteria. The second approval is a check against the plan. The agents can do all the work of taking the plan, breaking it down into tasks, building, and then verifying it. A good orchestrator will include people in the workflow at the points where their decisions matter and maintain a record of it. > — [geokos on hackernews](https://news.ycombinator.com/item?id=50256698) > Here's a question, to people who delegate all their coding to AI agents now: What are you doing to keep your mind exercised in all this suddenly new free time you have? Personally I find talking with agents extremely tedious and unrewarding; I would rather just write the code, even if it's simply because it's more interesting than playing Sudoku or whatever the fuck you do when you have nothing to do with your brain. And talking to AI agents is not the same as using your brain. It's frustrating, it seems to be intelligent, you think you're using reason with them, but it rapidly degrades your ability to reason. It encourages you to accept answers without checking them thoroughly. So much for the skills of accuracy and integrity you built up. It's a sugar rush. > — [noduerme on hackernews · 6 comments](https://news.ycombinator.com/item?id=50255819) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50255298) · 178 points · 135 comments ## Similar posts on daily.dev - [Agentic AI and The Mythical Agent-Month](https://daily.dev/posts/agentic-ai-and-the-mythical-agent-month-8rtsmjirr) · Metadata · 1 upvotes · 0 comments - [Mythical Man Month](https://daily.dev/posts/mythical-man-month-giqhim6fk) · Martin Fowler · 0 upvotes · 0 comments - [The Opposite of Brooks's Law: Removing…](https://daily.dev/posts/the-opposite-of-brooks-s-law-removing--ojrzagrzk) · Justin Searls · 0 upvotes · 0 comments - [Agentic Development: We Handed Off the Code, Not the Job](https://daily.dev/posts/agentic-development-we-handed-off-the-code-not-the-job-2ou02tzdx) · Atomic Spin · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs) ```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 Mythical Man-Month in the Age of AI","url":"https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs"},"datePublished":"2026-10-27T08:44:41.288Z","dateModified":"2026-10-27T11:31:08.125Z","description":"Brooks's Law still holds when you swap people for AI agents, the author suggests, but it mutates rather than vanishing. Brooks's 1975 claim, 'adding manpower...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1dad8e82bd5a0eaeb99d46b68f8d5c4c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1dad8e82bd5a0eaeb99d46b68f8d5c4c?_a=AQAEuop","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/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm","timeRequired":"PT2M"} {"@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":"The Mythical Man-Month in the Age of AI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-mythical-man-month-in-the-age-of-ai-iaswxpnhs#faq","mainEntity":[{"@type":"Question","name":"Does Brooks's Law still apply when you use AI coding agents instead of adding more developers?","acceptedAnswer":{"@type":"Answer","text":"Yes, it still applies but in mutated form. Sequential tasks remain sequential, so nine AI agents cannot finish a task faster than one agent working through it step by step, just as nine people cannot deliver a baby in one month. The overhead shifts from managing people to managing agents, including defining 'done', reviewing output, and catching hallucinations. Anyone orchestrating multiple coding agents can track this kind of thinking on AI-assisted development on daily.dev."}},{"@type":"Question","name":"What happens when you assign many autonomous AI agents to the same codebase without clear requirements?","acceptedAnswer":{"@type":"Answer","text":"Without clear orchestration, multiple autonomous agents working on a single codebase will rewrite each other's work in a high-speed loop. The proposed update to Brooks's Law captures the risk: adding agents to a project with unclear requirements gets you the wrong answer faster rather than a working solution sooner. Teams scaling multi-agent coding setups follow lessons like this on daily.dev before hitting the same mess."}}]} ```