Comment by theturtletalks
21 hours ago
With LLMs becoming prevalent, it seems people are “quitting” their projects more quickly. Not necessarily a bad thing, but just shows that the opportunity cost is too high right now if you’re building the wrong thing. Deno isn’t the wrong thing, but LLMs don’t reach for it and that’s a huge blow right now.
> Deno isn’t the wrong thing, but LLMs don’t reach for it and that’s a huge blow right now.
This only matters if you don't know what you are doing. LLMs can work with any tool. I'm working with a very unconventional stack and the LLM seems right at home.
They were talking from a product/company perspective where if Deno isn’t the default runtime that the LLM chooses for you, you tend to fall into obscurity.
That’s also probably why bun, supabase and netlify have been seeing so many new users, because (at least in my case and unless instructed otherwise), vibe coded projects had a tendency to push me in that direction.
I have a tech stack that I use and yes I tell AI to use it. But if I’m starting a new project and AI is doing the scaffolding, I’ll just let it decide what to use. It uses Bun a lot of the times. Many people will just go with what AI chooses, right or not.
Which stack is that?
I use kotlin for the web, mostly because I like working in kotlin and it lets me share a lot of code with my compose app and server.
LLMs don't reach for it because the frontier companies don't have it as the default. I've instructed Claude to NOT use React (use SvelteKit), NOT use Node (use Deno or Bun), among other things.
The industry defaults are trash but it is what it is.
They would rather have some unreadable python scripts and vendoring than using a package manager in a c++ project...
It also really really wants to use Gradle if you're making a Bukkit plugin, even though you really only need the JDK.
The only reason to ever touch it, are Android projects. I try to stay Gradle clean as much as possible.
4 replies →
HY SvelteKit
Oh man they all reach for the nextjs dumpster fire. Every single vibe coded app is that stack. At least many are backed with supabase (Postgres is a same choice).
I enjoy LLMs as much as the next guy but man, having a baseline of knowledge about coding goes a long way.
2 replies →
postgres is a sane choice, I can't type
This is part of how LLMs are hurting progress. People are moved away from things like StackOverflow or new projects where they pose and answer questions with real people, or create novel things, and pushed more and more to whatever answers or solutions the LLMs will spit out for them.
Also the less you know, the more your solution will be the same as everyone else’s.
I just throw Deno into my agents file and it gets installed in whatever environment I'm working in.
However, the truth is that writing isomorphic javascript programs in the age of agentic coding is much less important to me than it was a few years ago.
> LLMs don’t reach for it
Please excuse my language, but that's only the case if you're a complete imbecile and can't write a for loop to save your life.
An LLM doesn't "reach" for anything, because you tell it what to do. You go "use this tool, to do that thing, in this way, here's a bunch of written guidance on how exactly to do that, and if you run into issues ask me". Any other use is glorified copy-paste slop code and will end up with a worse codebase than if you let an egomaniac run amok on a single codebase for 20 years.
You are ignoring that prompting is fractal all the way down to the scale where the human writes everything by hand.
If I say, "start a C++ package skeleton" I'm getting CMake, not waf, make, bjam, or whatever. If I state the build system, then I'm still getting some package layout drawn from the training distribution. If I specify that, I'm still getting snake_case or CamelCase or whatever naming convention, drawn from the training distribution. If I specify that, etc etc.
It is distribution sampling all the way down.
So, yes, literally LLMs ARE reaching for "it".
This brings up the question how much weight these people have, if don't even know what their solution should be based on.
"Deno isn’t the wrong thing, but LLMs don’t reach for it and that’s a huge blow right now"
Well, in my case I suddenly had deno installed, while letting run fable in auto mode, even node was already there and I had to look up what deno was. "Ah, that node replacement."
I added a wrapper script around Deno to my agent’s allowlist to take advantage of its permissions system, and instructed it to use Deno instead of Python or bash commands. It’s worked pretty well.
Shouldn't be an issue. Like LLMs don't reach for uv, but they will if you make it clear you want to use uv.
sounds like you don't know about agent skills yet.