conrs

More like a super expensive version of Factorio for engineers. Everybody I know has a software factory now, and a whole bunch of software nobody wants :)

Love this post. Surprisingly controversial; it hasn't made me very many engineering friends.

Congrats! That's pretty cool.

I find in software the more constraints I can find the better the innovation ends up being, and business model is an excellent constraint - even just knowing what a responsible amount of effort is versus the value you anticipate.

Admittedly, I originally misunderstood your product as being more like google sheets - where it becomes a cloud drive of sorts with spreadsheets on top. At which point the risk of losing access to the tool would make adoption very unlikely.

The world runs on spreadsheets! How do you plan on sustaining the business?

Fair, my mistake.

I've built a lot with LLM's, my experience sort of but not really tracks that. I've had to course correct a few bad abstractions but the larger the code base becomes the better it seems to be at reusing things. Maybe this is because of types, or spec-first development (with OpenAPI), or black box integration testing - but also maybe not. But generally I have to think about the abstractions and let the LLM fill in the details with rare exception.

I think the trick here is plural; I guarantee no single human knows all 1 million lines. Note this is different than knowing how to orient yourself in a million line codebase quickly.

The limit here I think the ancestor comments are getting at is cognitive load, which is real and measured. We only have so much memory to devote to a "stack" when executing, and it's usually quite constrained.

Things like this have existed for awhile. The challenge is always rolling it out to peers. It's confusing to them, and kills their velocity. Just like functional programming paradigms themselves - objectively better, but also objectively more difficult to hire for.

Yeah, echoing the comments here. It's a good idea - kind of - but it is all about digging deeper when it is sus.

The tool assumes so much. That it is fine to kill a process itself versus just asking you to kill the process. That everyone MUST have passwords in their home directory. It's all meaningless without providing the thing it is running and so no activity is technically safe.

Why do people even get the agent to run the commands it asks to run? You can solve the entire threat vector by running it yourself and giving the agent the output. Claude practically only needs things like sed, awk, and grep. It's a pattern matcher. It's a waste of yours (and its) time to have it run your project.

yeah, I think there's the marketing and then there's the actual true utility. AI isn't a better computer program. It's not going to be able to do everything you want autonomously. But, it's pretty good at some stuff!

Fair. I have high hope for local inference, feel like right now it is simply cost prohibitive to get the hardware. It will be interesting to see what happens.

IMO It's a different and new model. We're engineers, and we're rich. It's not going to be good enough for us. But the much larger market by far is all the people who used to HAVE to work with engineers. They now have optionality; the pendulum is going to swing.

I'm curious - why for now? This stuff is practically commoditized. Trying to think of anything that ever successfully got back into proprietary land from there.

Nice, you beat me to this concept. I finally planted a flag and decided to dev entirely on an M3 with 8Gb.

It is completely feasible, and the battery life - amazing. Even when running a whole pile of Kubernetes services.