It's bad for building your resume. Managers and employees are rewarded for popular thing. Popularity is mostly a function of novelty. So the (social and therefore economic) incentive structure is inversely correlated with choosing boring technology.
Exactly. When I joined the company I'm at now (consumer energy industry), the energy crisis hit and the servers melted from all the people looking to fix their contracts etc. I wasn't directly involved, but loads of developers did a mammoth effort to rewrite old services to prevent this from ever happening again.
New energy crisis this year, the servers held, the company made a lot of money from new contracts via a combination of getting lucky with long-term buy-in contracts and the servers staying up unlike the competition. But there were no heroes, no praise to e.g. the developers putting in the extra hours, etc - it was business as usual, or business as it's supposed to be.
I've been noticing this as a solo dev. I need to put lots of work into infra and security, and all I get for it is... the thing not blowing up (hopefully!).
The work is invisible, and impossible to "show off", so it's a bit unrewarding and demoralizing. But hey, someone needs to do it!
And the worst part is, because it's invisible, a higher up manager will think "Ah, we don't need these people anymore, let's replace them with juniors, an external company, and/or AI". It's maddening.
It's why senior developers should end up in management or in positions of making decisions, but it's a completely different type of job to software development, where reason and objective truth and whatnot is barely relevant compared to social skills and connections. (this may be inaccurate, I'm not in that 'layer').
Exactly; I've seen a number of instances now of people pushing the hip new technology, but jumping ship (i.e. getting promoted, a new job, or a different assignment) shortly before or after the shiny new thing was "done".
In one case, ten years later, the company is still struggling to maintain their Scala applications in an environment where there's barely any Scala developers (and who charge a premium because it's specialist work), while the main author(s) went on to work at the company behind Scala itself. I'm sure Scala is great for specific use cases (just like every other non-top-10 language out there) but please, think very carefully before trying to build your company on top of it.
Try to explain that part of an imagined "Agentic AI Everything" product being built would be cheaper and more efficient as a simple function call. Good luck!
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.
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.
Note this is different than knowing how to orient yourself in a million line codebase quickly.
Hence my library mention. Humans have been doing this for millennia: orienting ourselves within a library (the physical kind, full of books) and calling upon its information resources as needed to accomplish tasks (research). Ultimately, it's all just one big cache hierarchy. Your short term memory, your long term memory, the book in your hands, the desk at the library, the nearby shelves, the card catalogue, the stacks, the inter-library loan system.
To manage it all, we humans have developed our abilities for abstraction. When we build clean, tight abstractions we reduce our cognitive load. Perhaps the best abstraction we've built so far is the TCP/IP and web stack. We don't need to care at all about the hardware details of a server in order to talk to it. It's such a powerful and airtight abstraction that we take it for granted.
I'd like to hear from more people who have spent a lot of time building with LLMs, because so far what people are saying is that these models do not have the ability to reason about and build the kind of marvellous abstractions us humans have built.
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 built a web-OS, a graphical IDE, and a version control system to replace git, all in about 40,000 lines of highly abstracted Javascript. If you're thinking about how important it is to be able to maintain million-line codebases, I suspect you might have substituted a metric for the actual end goal.
That looks like a nice feat, can you share a repo?
That said, reality at scale always come with details that will break the model, and the main roads when it happens are to ignore/reject any change proposal in the model, go in the mystic quest to reach a model that will fit it all including these new cases with an elegant simple solution, or accommodate special cases on the side until it grows too big or just percolate too fast in the main part to let it be sustainable.
This is an interesting idea. I'm building https://tend2thrive.com - I could see an interesting collaboration here. Always looking for ways to re-engage your network without it feeling heavy.
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.
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.
It doesn't look commoditized to me, it looks subsidized. It looks like everyone is trying to be "the one" and running as competitively as possible until the others fail. Commoditized would imply these services are all going to mellow into a stable state and mostly compete on price. I don't think that's happening. These aren't paper clips, they are courting governments and trying to pull the ladder up behind them. That's why both Anthropic and OpenAI are preaching doomsday and trying to build a moat with regulations.
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.
The thing is that AI is still more akin to a glorified autocomplete than something that can really supersede your skills. Proprietary model suppliers are constantly trying to obscure this basic underlying fact, without much success (much of the unpredictable shifts you see in proprietary AI behavior ultimately boils down to this); so it becomes far more crystal-clear when using open models that really are a pure commodity.
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!
