Stop building your own software factory and just ship something
Personal software factories are a waste of time
Engineers keep pouring time into personal AI-powered "software factories" that generate apps, but the author argues this is the last thing worth doing. A factory just extends the old habit of starting side projects and abandoning them. Non-developers are already using AI in wild ways, and the real skill to develop is finding problems worth solving. Building automation makes sense at work, where you understand messy systems and edge cases, not as a solo hobby.
The tough pill to swallow is that we've entered an era where everyday non-devs are applying AI in mind blowing ways and you still haven't built shit.
- nielsole
Everything is being rethought right now. So many paradigms are broken.
There wasn't ever a better time to build a software factory.
- ajmurmann
I think he's right in that the software factory somewhat should emerge. You shouldn't start a project by saying "well, I first should build a software factory to make this faster". Start by building the thing by directing an agent. If you find yourself writing the same thing over and over put it into a skill which you should think of and treat as a macro. When you find yourself developing clear patterns what skill gets invoked when it might be time to start a software factory which in essence puts those decisions and relevant informations behind a pretty interface.
My software factory emerged that way and for the 50-70% of simpler tasks I work on this saves me so much time and, more importantly, mental overhead.
- rc-1140
What I'm getting from the contents of the blog post is that there's a constant fight the author has with their audience that I'm summarizing as "I think your endeavor is foolish and you shouldn't do it, but I'm not your boss so who cares, but it's a bad idea, but it could be useful, but you shouldn't do it".
I think if you have plans for a software factory (read: some kind of conceptual framework for a loop that turns tasks into code/features), you should try it. My opinion is that even if your implementation is a bust or you never take it past a proof of concept, you've at least done something to inform yourself about what's out there and what you've tried.
Better to have a graveyard of barely started projects that give depth to your knowledge instead of relegating yourself to prompt slavery because [frontier model of the financial quarter] can do Marvel + Bioshock + Ted Lasso + Command and Conquer or whatever horrifying Consumptionslop™ that people like Nikita Bier love so much.
- codebastard
Sounds to me like people understand different things under a software factory.
I believe a software factory is just the next step in the mantra everything is code.
One wants to write a feature description and acceptance criteria into the "box" as fuzzy and with least details as much as possible.
To enable this, one creates for the factory access to information of the domain, requirements and software stack as required by the environment.
And this one attempts all with tools, documentation and processes optimized for the ai.
All with the goal use less tokens, context and speed up every action taken by an agent as much as possible.
That's why there is a trend to plugin based self evolving harnesses which try to automate this with opionated solutions.
Therefore I don't see a reason why building tools for easier testing and less tokens usage is a waste of time especially because one learns more a more areas in ones work one can automate and because depending on your tool choice it can be done without your input and one misses the chance to experiment if ones input in that regard will improve the factory or not.
- zem
I fully agree with the sentiment, but is it attacking a strawman or are people really building "software factories"? this is the first time I've even seen the term used in the context of LLMs. what would a software factory on top of an LLM even look like?