qudat

I’d say that, in all the ways that matter, I understand the code. Sure, if I had to hand-edit it now, there’d be a serious learning curve. But I won't have to.

Famous last words, but point is taken.

The non deterministic nature of an llm breaks the metaphor that they are like a compiler.

However, it’s not foreign to compilers to receive feedback from the running program (PGOs), so there are still parallels to the feedback we provide LLMs that guide their “optimization”.

I think even calling LLMs a non-deterministic compiler isn’t accurate either so ultimately I agree the metaphor doesn’t quite work.

I do think LLMs are like compilers in terms of how they changed how we build programs from a historical context. But that’s about it.

It’s been great for llm + cli usage on mikrotik

The component trees have to be rewritten, only the non-view related JS code can be reused.

You can do damage tracking for TUIs. Printing to the terminal is done by moving the cursor and redrawing the line the cursor is on.

Very cool! I run a set of ssh-based services over at https://pico.sh and love seeing all the indie web content on HN!

Sftp is still very useful even in 2026

There’s not much of a difference because open models are distilling from frontier models. If frontier models cease to exist then many of these open models will as well

I just use https://tuns.sh which has a handy bash script to make the ssh tunnel simple

My main point is that following the spec doesn't guarantee shell scripts will be portable, which is a common misconception.

That feels like a failure in the spec. Your example illustrates it: echo has unspecified behavior that literally prevents it from being portable.

Is it possible portability is just not a feature of posix?

This is quite a timely post compared to: https://bower.sh/posix-shell-is-all-you-need

This post was thought provoking, I wonder, is the hidden argument here that the posix spec for a shell is not well specified if there is so much variance between the implementations?

Or is the fundamental issue simply a matter of history? Both?

Bindings are not IPC. The Deno runtime and the rendering backend run as threads / processes inside the same address space (CEF) or coordinated process group (WebView). Calls go through in-process channels, and the backend dispatches them from its run loop. -- https://docs.deno.com/runtime/desktop/bindings/

I don't understand how the coordinated process group works. Doesn't that mean in this multi-process mode it must be IPC? Maybe the claim "shared memory space" is more an architectural description than an OS-level claim?

Major props to Mitchell (and his family) for these donations.

I put my SS in there

Anyone know the song that's playing in the demo?

I feel like the claims come from wildly different personas and use cases. A 24gb vram, 5 year old titan run 27b at 30t/s and the results are good. I use sonnet and opus at my day job and they are more capable but I can still get the same out of qwen, I just need to be mindful of ctx

I don’t bother with wrappers, why does it need to be easier than git clone + makepkg -i?

Then I just update when I need to update

Excellent ad campaign by Anthropic

Preload is the answer to speed. Basically download the clients db on init and then have cache invalidation strategies. I built starfx to basically perform the data sync aspect of this paradigm https://starfx.bower.sh/learn#data-loading-strategy-stale-wh...

I really like this idea and have been experimenting with it over a week or so.

I think there’s an opportunity to use an AST diff system for code forges where you don’t present the user with line diffs in the UI — or at least not as the first diff the user sees.

I firmly believe code review should happen in your editor.

I'm still thinking this through but I was arguing this position to colleagues to some shock: LLM's are a race-to-the-bottom and frontier models will not be able to afford to work on coding specific models (or coding features at all) in the very near future.

27B is already really good at coding-specific tasks. Fundamentally, there is little innovation on the core architecture: LLMs are all designed essentially the same, with minor differences in how they are trained. They are all feed-forward multi-headed attention models; it doesn't matter if it's a 4B model or a 1T model, that's just scale.

Further, the frontier models cannot afford to innovate: they have to scale as quickly as possible to "beat out" their competition. The frontier models fundamentally will not create the next "attention is all you need" monumental jump in AI.

Frontier companies are stuck on scale with zero capacity to innovate. You cannot point capitalism at "basic science research" and expect any ROI. This is a known reality. Innovation is much more indirect and a "random walk" style of knowledge acquisition.

Finally, these LLMs are quite literally designed with a human-in-the-loop, and we do not give ourselves enough credit for how well we ourselves tool-call. We are doing a lot of heavy lifting to make these models useful and you cannot simply remove us from the equation without also removing ourselves from the training pipieline.

I built https://zmx.sh to make it easier to interact with your terminal sessions programmatically. 1 window = 1 session which might feel like a negative but it makes programmatic access easy and agents can use it just by pointing it at the zmx help command. Basically, an agent just needs 2 commands (run and write) for full control and the commands are synchronous so you don’t need to do any polling.

And a labeling action which requires `pull_request_target`: https://github.com/actions/labeler#create-workflow

These types of features are not worth it and need to be removed from the marketplace.

Literally the model “mythos” is being marketed towards finding these exact type of bugs used for exploitation. I really don’t understand the argument: are agents not good at findings memory management issues? What’s the gap?

My guess is it won’t be worth it to focus specifically on coding models once local small models work just as well or within range. That will naturally close the gap even more

Yep. I’m approaching the same problem from a different angle: writing code fast means you aren’t being thoughtful about the features you’re building. I started realizing that after I had kids and spent more time thinking about code than writing it and it really improved the quality of my work: https://bower.sh/thinking-slow-writing-fast

Nah. These agents are getting easier and easier to run local. Have you tried Qwen 3.6 27b? It’s insane what it can do compared to its size. Like 100% vibe small projects if you manage context properly.

These models are a race to the bottom just like compute.

I don’t understand: just use an agent to find all memory leaks and segfaults. I don’t get the argument if you are gonna vibe code anyway.

With unlimited tokens make it a lint rule or auto formatter.

We take a slightly different approach for https://pico.sh -- no automatic subscription, but we charge for an entire year. It's great for us because each sub is a year and if someone truly isn't using our services then it'll quietly drift into the background for the end-user.

The entire concept that we need to cater CLIs to agents at all should tell us how far away they are from being “junior devs” or “an intern” and I reject the premise.

A lack of structured output has never been a blocker for agents to work, that’s a traditional coding problem.

“Write good help text and error messages” is just good design which is self evident.

I don't get it, it looks like they are copying data to the sandbox filesystem why would that impact production data? Because the agent can re-upload the file to s3?

Wild example as it has been corrupted by VC money as well. I wouldn’t touch deno either.