It's interesting to revisit Brooks' "surgical team" in light of AI. For example, I frequently have Claude act as a "toolsmith", creating bespoke project-specific tools on the fly, which are then documented in Skills that Claude can use going forward. What has changed is that a) One person (or rather, one person-AI hybrid) plays all the roles within the surgical team, and b) Internal frictions such as cost, development time, and communication overhead have all been dramatically slashed.
Notably, his essay “no silver bullet” states that there has never been a new technology or way of thinking or working that has led to a 10X increase in the speed of software development.
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.
I'm curious to check how faster AAA games will hit the market in the next years compared to the pre-LLM era. Or how much of the aging COBOL code base out there will disappear in the next decade.
When concrete things like that start to happen, then I will start to believe in the 10x claim.
This was true as programming languages evolved too. It was so much easier to write scripting languages than C. You could crap our scripts like crazy - no cc refusing to give you a binary to get in your way.
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.
Most of my work has been in core infra at large companies. Having the code written faster does not change rollout velocity all that much... It does help with signals and idiot proofing on bugs but when things break and cost real (very real) dollars AI is not an explanation. In that instance, its not even close. Development might be 10-20 percent of the actual work to get a change out.
Code is always easy to multiply fruitlessly, always has been.
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.
Writing code is a part (sometimes a big part, sometimes not) of delivering software to production. The overall system throughput is the interesting thing to look at.
I've been thinking about this and have wanted to discuss it with people.
I think the 10x thing has been broken, but I don't think it's because the premise of "No Silver Bullet" was false - I think it's because LLMs have the ability to navigate some of the _essential_ complexity of problems.
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?
The premise of "no silver bullet" is wrong (LLM just made it clear, but it has always been wrong).
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.
I agree with this sentiment but I think LLMs are really close to the Brooks idea of a silver bullet.
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)
"claude, connect to a k8s pod in prod and grab a 30s cpu profile, analyze and create a performance test locally for the top outlier, verify your fix and create a PR"
Fortunate to be reminded of this right now, especially the pull-quote about conceptual integrity.
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.
As a software engineering manager, 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. If some things take longer than expected, then I already have a team of engineers with all the context since the project kicked off that can help each other with any longer running tasks. An engineer that has completed a smaller chunk of work can help out with the items on the critical path, for example.
>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.
The bearing of a child takes nine months, no matter how many women are assigned.
For the human makers of things, the incompletenesses and inconsistencies of our ideas become clear only during implementation.
Conceptual integrity is the most important consideration in system design.
There is no single development, in either technology or management technique, which by itself promises even one order-of-magnitude improvement in productivity.
---
These ideas still apply very well to modern society.
but,
Personally, I hope science advances to the point where nine women really can have a baby in parallel.
We may need that to prevent demographic collapse and keep the pension system from running out of money.
Nine women can already have babies in parallel. That is, nine women cannot have a baby in one month, but nine women can have nine babies in nine months.
It would probably be more practical to make old age less expensive than to inject more people into the bottom of the demographic pyramid. Those young people eventually get old too. I am looking forward to my sentient robot caretaker:
"The programmer, like the poet, works only slightly removed from pure thought-stuff. He builds his castles in the air, from air, creating by exertion of the imagination." -FB
Indeed a lot of things have changed. A worthwhile exercise is to read the book, contemplate how things have changed, and try to map lessons from the book onto modern technology and organizational practices. A LOT of the core principles are still relevant IMO, even if many of the implementation details are not.
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.
When concrete things like that start to happen, then I will start to believe in the 10x claim.
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.
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
there are entire C corps of monkeys out there
Also, I know that there will be a lot of boilerplate applications that just don't look good or seem to have been well thought out early on.
Folks will use that as a cope mechanism, but huge changes are coming.
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?
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.
> 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)
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.
For the human makers of things, the incompletenesses and inconsistencies of our ideas become clear only during implementation.
Conceptual integrity is the most important consideration in system design.
There is no single development, in either technology or management technique, which by itself promises even one order-of-magnitude improvement in productivity.
---
These ideas still apply very well to modern society. but, Personally, I hope science advances to the point where nine women really can have a baby in parallel.
We may need that to prevent demographic collapse and keep the pension system from running out of money.
“Open the refrigerator door, HAL”
“I can’t do that right now”
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.