> They are young and inexperienced today, but won't stay that way for long.
I doubt that. For me this is the real dilemma with a generation of LLM-native developers. Does a worker in a fully automated watch factory become better at the craft of watchmaking with time?
I think the idea that LLMs are just good at "automating" is the old curmudgeon idea that young people won't have.
I think the fundamental shift is something like having ancillary awareness of code at all but high capability to architect and drill down into product details. In other words, fresh-faced LLM programmers will come out the gate looking like really good product managers.
Similar to how C++ programmers looked down on web developers for not knowing all about malloc and pointers. Why dirty your mind with details that are abstracted away? Someone needs to know the underlying code at some point, but that may be reserved for the wizards making "core libraries" or something.
But the real advancement will be not being restricted by what used to be impossible. Why not a UI that is generated on the fly on every page load? Or why even have a webform that people have to fill out, just have the website ask users for the info it needs?
But do those watches tell time better? or harder? or louder? Once you have the quartz crystal and have digital watches, mechanical movements became obsolete. Rolex and Patek Philippe are still around, but it's more of a curiosity than anything.
I use Coolify for my own personal static site and it’s just like that. Git pushes redeploy my site and I get a discord notification once’s it’s done. The only manual thing I did was use a cloudlfare tunnel So it’s available to the public, since I am using my homelab to host Coolify.
I host maybe 8 different side projects on Coolify like this. Most don’t even have a Dockerfile in the repo. I use the standard nix packs option, and builds, rolling deployments etc are auto handled.
This seems like an unfair comparison for Dokku. I haven’t used the rest, but I have used Dokploy and Dokku. Dokku has had every single feature I could want or need, even accounting for weird edge cases. It just doesn’t have a UI.
With Dokploy, on the other hand, I found the UI difficult to navigate, which would be fine if the documentation was good but it was lacking.
But for many of the features their comparison claims Dokku doesn’t have, it actually does: database support, scheduled jobs, docker compose support. It has some form of monitoring. Overall Dokku has been a pretty robust solution for me and anything it might be missing, like in monitoring for instance, I can just add at the system level.
To be clear, I’m not anti-Dokploy and I think the more these tools improve the better. Just wanted to share my experience in defense of Dokku. Being able to spin up your apps on a cheap VPS is incredibly empowering over having to pay 10x more for managed services like Heroku or Render.
Interesting, never knew about that! I filled out my details, then went to https://huggingface.co/openai/gpt-oss-120b but I'm not sure if I see any difference? Where is it supposed to show if I can run it or not?
Maybe I'm spoiled by having great internet connection, but I usually download the weights and try to run them via various tools (llama.cpp, LM Studio, vLLM and SGLang typically) and see what works. There seems to be so many variables involved (runners, architectures, implementations, hardware and so on) that none of the calculators I've tried so far been accurate, both in the way that they've over-estimated and under-estimated what I could run.
So in the end, trying to actually run them seems to be the only fool-proof way of knowing for sure :)
While it is seemingly hard to calculate it, maybe one should just make a database website that tracks specific setups (model, exact variant / quantisation, runner, hardware) where users can report, which combination they got running (or not) along with metrics like tokens/s.
Visitors could then specify their runner and hardware and filter for a list of models that would run on that.
Have to practice attention hygiene. Add blockers, switching to something else if add or woke crap pops up. Annoying audio adds in shops.. I start singing to myself to keep verbal part of the brain busy.
