Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mythical Man Month

martinfowler.com

Post reply on HN
Print view View original

111–120 of 219 posts

Re: Mythical Man Month

#111

Post by dnnddidiej »

aerhardt wrote: post #108
jwr wrote: post #104

I re-read that book every 10 years and try to think carefully about whether what Brooks wrote still holds. 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 Broo…

Dario Amodei said in the most recent interview with Dwarkesh that Anthropic currently gets achieves an increase of around 20-30% coding productivity, which tracks with my experience. What do you do to reap orders of magnitude more? Also, how much more money do you make? Or are you working less?

I think if you build out simple sites it is 10x. That number tends to 1x as the project gets more complex.

Side projects where you try an idea are you not finding 1h now to do what was 10h work?

Re: Mythical Man Month

#112

Post by Towaway69 »

chickensong wrote: post #105
Towaway69 wrote: post #70

Earlier quoted context omitted.

I think your answer is the reason why. LLM performance is fine when applied to everything they can do. 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.

Right, I get that. I'm just saying it seems wrong to throw up minority examples. Nobody is pumping out AAA games at speed with LLMs, nor is anyone claiming to do so. There will likely always be some areas where LLMs are bad or useless. How many people are writing crud apps using mainstream languages vs COBOL though? You don't need 100% silver bullet 1-shot everything, just to recognize the signals that for many use c…

Definitely the safe space is expanding but how fragile and expensive is this expansion?

AI requires a larger amount of fragile resources to work as opposed to an editor, keyboard and a human.

It some sense it’s a bit like the bitcoin revolution that slowed down once transaction times ballooned out. And blockchains didn’t replace databases as expected. Probably for very good reasons: resources required v. results delivered.

I personally agree that AI is great technology for some great new tools. But we still haven’t found its limits: cost v. results. That happened with bitcoins and blockchains is still outstanding for AIs.

Re: Mythical Man Month

#113

Post by ilitirit »

"Conceptual integrity" is something I always try to adhere to when I design and build systems. I also use it also a bit of an indicator when gauging someone's experience. For example, mid-level devs will often try to introduce some form of "optimisation" somewhere in the codebase that results in the codeflow deviating from existing patterns. More often than not I will reject the PR, or the idea. For me, it's better than all flows follow similar paths. It makes it easier to reason and communicate ideas about, modularise and/or form logical groupings etc etc.

This is also why one of my instructions to coding agents is that they adhere to established coding and testing patterns, even where they appear to be sub-optimal.

Re: Mythical Man Month

#114

Post by freedomben »

rafaelmn wrote: post #80
nemo1618 wrote: post #46

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, developmen…

How well does that work for you ? It's annoyingly inconsistent for me - I give it instructions on how to fetch JIRA ticket with a script that renders everything relevant to a .md and half of the time it will still default to reading it via ACLI. I have instructions on how to do a full build with warnaserror before commit but I still get pipeline errors regularly because it will skip the noincremental part, etc.

I've had that happen before too, and I just added a line to CLAUDE.md or AGENTS.md something like (adapted to your example):

    When asked to fetch JIRA tickets, use the "fetch-jira" skill rather than reading via ACLI
Claude has gotten better about following CLAUDE.md over the last year (it was pretty laughably bad at it previously).

Re: Mythical Man Month

#115

Post by maccard »

freedomben wrote: post #114
rafaelmn wrote: post #80

Earlier quoted context omitted.

How well does that work for you ? It's annoyingly inconsistent for me - I give it instructions on how to fetch JIRA ticket with a script that renders everything relevant to a .md and half of the time it will still default to reading it via ACLI. I have instructions on how to do a full build with warnaserror before commit but I still get pipeline errors regularly because it will skip the noincremental part, etc.

I've had that happen before too, and I just added a line to CLAUDE.md or AGENTS.md something like (adapted to your example): When asked to fetch JIRA tickets, use the "fetch-jira" skill rather than reading via ACLI Claude has gotten better about following CLAUDE.md over the last year (it was pretty laughably bad at it previously).

It only released just over a year ago…

Re: Mythical Man Month

#116

Post by rafaelmn »

freedomben wrote: post #114
rafaelmn wrote: post #80

Earlier quoted context omitted.

How well does that work for you ? It's annoyingly inconsistent for me - I give it instructions on how to fetch JIRA ticket with a script that renders everything relevant to a .md and half of the time it will still default to reading it via ACLI. I have instructions on how to do a full build with warnaserror before commit but I still get pipeline errors regularly because it will skip the noincremental part, etc.

I've had that happen before too, and I just added a line to CLAUDE.md or AGENTS.md something like (adapted to your example): When asked to fetch JIRA tickets, use the "fetch-jira" skill rather than reading via ACLI Claude has gotten better about following CLAUDE.md over the last year (it was pretty laughably bad at it previously).

I have that both in the skill and in CLAUDE.md but it's not reliable - and polluting CLAUDE.md with task specific instructions kind of sucks.

Re: Mythical Man Month

#117

Post by oleggromov »

sutro wrote: post #19

"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

When I was young, in my teens, I already knew a bit about programming but of course nothing about the industry.

These beautiful metaphors by Brooks, from books like inmates running the asylum, etc - they made me romanticize the industry I had no idea about.

Now, about 20 years later, I wonder to which extent they influenced me to take the path I've taken. Because when I began, it wasn't lucrative or cool in the slightest.

Re: Mythical Man Month

#118

Post by OtherShrezzing »

aryehof wrote: post #82
OtherShrezzing wrote: post #76

Earlier quoted context omitted.

You’re describing output while the essay is discussing productivity. 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?

Salary stays the same. A bunch of others are fired. You’re expected to produce their level of output as well as your own. After all, you’re 10x more productive now?

I guess the follow up question to this is “have nine of your colleagues been fired?”

Re: Mythical Man Month

#119

Post by DeadEye2111 »

The funny thing is that adding agents to an AI-first project has similar issues (today). Agents stepping on each others toes, needing to manage state, communicate with each other, and divide up work that is planned ahead centrally. Agents accelerate, but don't reinvent the fundamentals of building products.

Re: Mythical Man Month

#120

Post by Deeds67 »

hansvm wrote: post #47
alasdair_ wrote: post #8

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 haven't yet seen anyone with a concrete example project (public ideally, but even describing private efforts in enough detail to enable potential criticism would be fine) making a claim as strong as 10x. Are you willing to break the mould and show us what we're all missing?

I'm building an open source Google Photos alternative. Have a look at my project and tell me if you think you could do all this at the same speed without an LLM: https://opennoodle.de

Direct github link: https://github.com/open-noodle/gallery

Post reply on HN