DE version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
69% Positive
Analyzed from 4265 words in the discussion.
Trending Topics
#code#more#software#development#claude#project#output#still#things#those
Discussion (104 Comments)Read Original on HackerNews
The last three times I read the book, everything held.
This time, I'm not so sure: AI does change things significantly. Perhaps not for all teams and not all scales of software, but in my case (solo developer, complex software system) I did measure a 12x productivity increase [1].
Also, some of the problems Brooks describes became much easier, if not borderline trivial with AI. For example, maintaining design documentation that stays consistent with the software being built. I do this and it is no longer a problem.
I still think most of what Brooks wrote is applicable today. I think the biggest difference is that AI enables smaller teams to work on larger systems, and the biggest benefit is for single-person teams (ahem) like me. I see it as another step that allows me to tackle larger systems: the previous one was Clojure which reduced incidental complexity so significantly that I was able to develop the system to the size it is today. AI is the next step: it allows me to build features that would have taken me years in a span of months. Not because of "vibe coding", but primarily because I can work on a set of design documents and turn my ideas into a coherent design.
[1] For the nitpickers: yes, measured, not guessed. Yes, the metric was reasonable. No, it wasn't "lines of code" or something equally silly, in fact one of my main goals is reducing code size as much as possible. Yes, I compared larger time periods: 2 months with AI to an average of 12 months of the previous year. No, the metric wasn't gamed: this is a solo business and I have no interest in gaming my own metrics. I earn a living from this work, so this is as objective as it gets.
Also, how much more money do you make? Or are you working less?
Side projects where you try an idea are you not finding 1h now to do what was 10h work?
When I find claude is using tools or approaches that I have replaced with more specific ones, I ask claude to add a hook to prevent doing this in the future and point it to the instructions of what to do instead.
And of course I wrapped all that up in a Skill so it knows what approaches to take to add things to hooks.
It becomes fairly trivial to incrementally stop it making repeated mistakes like this.
Then codify this behavior into a process which automatically gets run through.
I.e. $repo/origin as bare repo, then prompt to create a shell script which creates the worktree and cds into it, running the script you mentioned, instantiating pi in it. Potentially define explicit phases for your workflow and show the phase in the UI - and quality gates for transitions. Eg force the implment to finalize phase to only happen if all tests succeeded. Potentially add multiple review phases here too, with different prompts. This progressively gets rid of more and more inconsistencies.
Still not a perfect solution, but on average I've had less and less to manually address with that workflow. Albeit at cost of tokens (multiple reviews phases obviously ingest all changes multiple time)
Pi-agents extensibility is just a lot better then the other harnesses, but you could obviously also just introduce a different orchestrator to do the same. For me, pi-agent was just the least amount of effort necessary to get it going.
It seems like if you write the docs yourself that's not leveraging the probability that the model itself knows the anti-context guard rail that best prevents it from grabbing its average tool use.
That was true for almost seventy years until roughly last year.
AI is the silver bullet - my output is genuinely 10X what it was before claude code existed.
Assuming 10x on the speed of dev, Is the vscode repo a decent example? Recently they've been all in on AI augmented development so i'm thinking they'd be a reasonable subject?
How do you isolate out what counts as the "development" part of their delivery cycle (is that the dev inner loop, does that show up in frequency of commits then?) to measure it and see if it's running 10x?
https://github.com/microsoft/vscode/graphs/contributors?from...
One of the latest things I made with Claude was a tool that allowed me to move a bunch of very low traffic Cloud Run services to a single VPS without losing any of the Cloud Run benefits such as easy Docker-based deployment and automatic certificate provisioning. I thought about making something like that for quite some time, and Claude finally made it possible, which makes me quite happy.
The fun thing here is that no other soul genuinely cares about it, or any other code I might publish. The code, especially AI generated, is so cheap that if anyone wants to repeat my steps to get rid of Cloud Run services, they will probably vibe-code their own tool instead of figuring out how to use mine, just like I did that instead of spending time on learning Dokku or similar solutions.
So, yes, 10x and more, but no one cares about the result, which makes the whole 10x measurement less useful.
1. I would not have attempted this without AI assistance because it's a big project.
2. I have built a functional program that I am able to use for real work in a handful of weeks, working part time on this (like literally a few hours per day prompting Claude and Kimi).
3. Had I decided to do this without AI assistance it would have been months of work.
Complete frontend + backend + database.
Yes, it is an internal app, but it works and everyone loves it.
Does that count as an example?
(Also I absolutely expect him to need help at some point, but so far it has taken his project from absolutely impossible to 3 weeks of work in between work, renovating his house and being a dad for the first time so I was very impressed.)
https://github.com/KeibiSoft/KeibiDrop
It took me 2 years ago around 2k hours to build a cross platform FUSE vault, without using AI assisted tools.
The pain was debugging through logs and system traces. And understanding how things work.
Now managed to ship this one much faster, as an after hours project. Started it in may 2025, and around end of November 2025 started using claude on it.
Just by dumping logs into claude, and explaining the attack vector for the problems, saved me the FML moments of grindings walls of syscalls on 3 platforms.
I would say much easier to progress, and ship with the same rigour, minimize my time, focus and brain power involvement such that I can put the energy somewhere else.
We decided to integrate our SaaS into Microsoft Business Central and NetSuite as plugins into those systems. BC has its own programming language, called AL, that has a lot of idiosyncrasies from any other language I've worked with. And NetSuite plugins are written in SuiteScript, which is a custom JS runtime with a ton of APIs to learn.
In the "before", it would've taken 5 developers a year or more to build those integrations. I did both by myself in well under a year. Thank you Claude.
When I measure software dev, delivery of code isn't even a metric I care about. It is a key part of the process, to be sure, but I care about results - Did we ship? Did it work? Do we have happier customers and a smaller bug list?
In my experience, while I can answer "yes" to those questions on people who use AI assistance surgically, applying it where its strengths lie... I can answer an emphatic "No" for the teams I've worked with who are "AI-first", making the AI usage itself part of their goals.
When concrete things like that start to happen, then I will start to believe in the 10x claim.
I don't think we'll see AAA game velocity change until asset generation progresses quite a bit, not to mention stuff like rigging. Even then, there's still a layer between code and engine where you have to wire everything together which an LLM will struggle with.
Replacing some old COBOL is probably more of a management decision based on appetite for change and politics rather than development speed.
Aren't there some measurable things like github repo creation, PRs, app store additions, etc. that can be correlated to LLM adoption? Didn't Show HN have to get throttled after LLMs arrived?
Take LLM out that safe space and suddenly they are no silver bullet, in fact they are unless.
So of course those making the 10x claim mean in the safe space where LLM can handle all activities required. You can’t have it both ways 10x and difficult and confusing tasks for LLMs.
So increasing individual output by itself is not enough to affect the argument. It could, if you also reduce the size of people needed for a project, where people are everyone included in the project, not just SWE. But there are strong forces in large orgs to pull toward larger project sizes: budgeting overhead and other similar large orgs optimize for legibility kind of arguments.
IMO the only way this will change is when new companies will challenge existing big guys. I think AI will help achieve this (e.g. agentic e-commerce challenging the existing players), but it will take time.
At _this_ moment, AI is in the state of producing things - if you like with factor 10 or more. But what will come afterwards, when all this mush of code shall create _reliable_ results. This means not man month then, rather man years or decades to fix this billion and maybe trillions lines of opaque probabilistic LOC. You have to take the mean of these two stages, if nothing qualitative happens to the models.
I’m being glib, but there’s a whole class of software (eg simple crud apps) that just don’t have any marginal value anymore. So it doesn’t matter if it’s 10X faster or 100X faster. 100 x $0 is still 0.
Which is what I’m seeing at my job. All of these “afternoon vibe code” projects never actually get users because everyone just vibe-codes their own.
Clearly..it still wasn't a silver bullet. Because output as a metric is a bad one. I thought it was only one managers valued..but apparently Anthropic has convinced devs to value it finally? i guess it def hits that dopamine receptor hard.
But after people's expectations adjusted it was just back on the treadmill.
I don't think we've found a new steady-state yet, but I have some gut feeling guesses about where it's going to be.
In my experience stuff like RAILS had negligible impact in my field because companies would always require solid backup from some big name vendor (MS, Oracle, IBM, Sun - back in the day, or even SAP).
So most if not all the smaller silver bullets did not even make a blimp on the radar... and stuff like Java or .NET, while definitely better than C or COBOL... did not really deliver in terms of productivity boost (in part because, as noted in the message I am answering to, expectations kept growing at the same pace)
I remember when coding was free as in beer and freedom!
If you’re 10x more productive, someone is willing to pay you 10x as much as they were last year, because you’re producing 10x as much value as before.
Has your salary increased 10x?
You should expect this to be reflected in the labour market somewhere. Maybe not your own salary, but in somebody’s salary.
I too can vastly increase my speed of development when I stop caring about the quality.
Features are harder to show the limits of, but have you ever had a client or boss who didn't know what they wanted, they just kept asking for stuff? 100 sequential tickets to change the contrast of some button can be closed in record time, but the final impact is still just the final one of the sequence.
Or have you experienced bike-shedding* from coworkers in meetings? It doesn't matter what metaphorical colour the metaphorical bike shed gets painted.
Or, as a user, had a mandatory update that either didn't seem to do anything at all, or worse moved things in the UX around so you couldn't find features you actually did use? Something I get with many apps and operating systems; I'd say MacOS's UX peaked back when versions were named after cats. Non-UX stuff got better since then, but the UX (even the creation of SwiftUI as an attempt to replace UIKit and AppKit) feels like it was CV-driven development, not something that benefits me as a user.
You can add a lot of features and close a lot of tickets while adding zero-to-negative business value. When code was expensive, that cost could be used directly as a reason to say "let's delay this"; now you have to explain more directly to the boss or the client why they're asking for an actively bad thing instead of it being a replacement of an expensive gamble with a cheap gamble. This is not something most of us are trained to do well, I think. Worse, even those of us who are skilled at that kind of client interactions, the fact of code suddenly being cheap means that many of us have mis-trained instincts on what's actually important, in exactly the way that those customers and bosses should be suspicious of.
* https://en.wikipedia.org/wiki/Law_of_triviality
Extreme example, but exemplifies point
I don't think anyone has really wrestled with the implications of that yet - we've started talking about "deskilling" and "congnitive debt" but mostly in the context of "programmers are going to forget how to structure code - how to use the syntax of their languages, etc et etc)." I'm not worried about that as it's the same sort of thing we've seen for decades - compilers, higher-order languages, better abstracts, etc etc etc.
The fact that LLMs are able to wrestle with essential complexity means that using them is going to push us further and further from the actual problems we're trying to solve. Right now, it's the wrestling with problems that helps us understand what those problems are. As our organizations adopt LLMs that are able to take on _those_ problems - that is, customer problems, not problems of data, scaling, and so forth - will we hit a brick wall where we lose that understanding? Where we keep shipping stuff but it gets further and further from what our customers need? How do we avoid that?
Lean development theory teaches us that in a multi-workstream, multi-stage development process, developers should be kept at roughly 65-75% utilization. Otherwise, contra-intuitively, work queue lengths increase exponentially the closer utilization gets to 100%. The reason is that slack in the system absorbs and smooths perturbations and variability, which are inevitable.
Furthermore, underutilization is also highly comparable to stock market options: their value increases as variability increases. Slack enables quick pivots with less advance notice. It builds continuous responsiveness into the system. And as the Agile Manifesto tells us, excellent software development is more characterized by the ability to respond to change than the mere ability to follow a plan. Customers appreciate responsiveness from software vendors; it builds trust, which is increasing in value all the more with the rise of AI.
But AI-driven development threatens to increase, not decrease individual engineer utilization. More is expected, more is possible, and frankly, once you learn how to guardrail the AI and give it no trust to design well analytically, the speed a senior engineer can achieve while writing great code with AI assistance often feels intoxicating.
I think we're going to go through a whole new spat of hard, counterintuitive lessons similar to those many 1960s and 70s developers like Fred Brooks and his IBM team learned the hard way.
> AI is the silver bullet - my output is genuinely 10X what it was before claude code existed.
Those are not the same.
You can add 5 different features to a project and still provide less value that the 5 lines diff that resolves a performance bottleneck.
I don't know if, overall, it's a 10x improvement or 6x or 14x but it's a serious contender. Part of it is the LLMs are very uneven in their performance across domains. If all I build is simple landing pages, it might be a 100x improvement. If I work on more complex, proprietary work where there aren't great examples in the training data then it might be a 10% improvement (it helps me write better comments or something)
You still have to read the output of your LLM. Learning by reading alone and not doing is not nearly as effective.
The premise is that the software development had been mostly "essential complexity" rather than "accidental complexity." But I think anyone who worked as SE in the past decade would have found the opposite is true.
It's not only that software development is full of accidental complexity. Programmers (and the decision makers above them) have always been actively creating accidental complexity. Making a GUI program hasn't gotten easier since Visual Basic. In fact for each JavaScript framework and technique that wraps around DOM render engine, it has got harder over years. Until LLMs made it easier again (by creating a permanent dependency on LLMs. If you intend to edit the code manually afterwards, it became even harder!)
This is the reason why AI-assisted programming has not turned out to be the silver bullet we have been hoping for, at least yet. Muddled prompting by humans gets you the Homer Simpson car you wished for, that will eventually collapse under its own weight.
I've been thinking a lot about Programming as Theory Building [0] as the missing piece in AI-assisted engineering. Perhaps there are approaches which naturally focus on the essence while ignoring the accidents, but I'm still looking for them. Right now the state of the art I see ignores both accident and essence alike, and degrades the ability to make progress.
Please inform me if there are any approaches you know that work! And lest this sound pessimistic, far from it. This state of affairs is actually intoxicatingly motivating. Feels like we have found silver, and just need to start learning to mould bullets.
[0] Another classic required reading of the industry https://pages.cs.wisc.edu/~remzi/Naur.pdf
>I always look to staff up a project at the beginning as much as possible, looking for doing as much in parallel up-front as we can.
Ah, maybe this is what you think he would take issue with? Fair enough. Perhaps I should have said:
>I always look to staff up as much as is economically and organizationally optimal, to exploit all genuine parallelism opportunities, being careful not to overstaff.
Vibe coded software is the Marvel green screen movie equivalent.
Fred Brooks wrote that book when they were programming IBM operating systems in assembly language.
Times have really, really changed - do not pay attention to the messages of this book unless for historical fun.
That book isn't, it's built from humility and a rare bright light in this god forsaken field.
Martin Fowler, the author of the blog, may be a bit different than that.