qudat

Yes and this month I hit my $10 AI assistant cap for the first time, which is why I started looking around for other options.

I do like Kagi but the Gemini deal was too good to pass up as it also gives my a code agent.

Hi, you're right. I've been self-promoting on HN too much without any other contributions, which isn't right.

I'm going to spend more time contributing without so much self-promotion.

Thanks for the feedback.

> Or maybe models get so good that a 30B model is genuinely smart enough to do everything, so nobody really needs a model like Opus or Sol unless they’re trying to solve the Reimann Hypothesis. I don’t really buy this. Models can do frontier mathematical work today while still being not smart enough to refactor large codebases as well as me, so it’s hard to imagine a world where I don’t just want to use the smartest model available.

Idk, I already don’t bother with Opus and stick with sonnet med. I really care more about speed. I use qwen3.6 27b for personal projects and I think it works pretty great.

So like the article mentions, if scaling stalls and small models get better it’s not impossible to imagine a convergence and hardware costs drop.

Having said that, self hosting will be a niche thing like it is today for other services.

Funny as I just cancelled my Kagi sub to get the Gemini ai pro sub. The deal was too good to pass up

I’m iterating on a constellation of git collab services that I’m calling “the disappearing code forge.” All self hostable with a focus on minimalism and Unix philosophy.

I just revamped the collaboration portion which is a patchbin service: https://pr.pico.sh

As part of that I work im also iterating on the ci/cd solution we are calling pici: https://ci.pico.sh

AMA

https://prose.sh for an ssh app to manage a blog

Try https://zmx.sh for a more minimalist tool

Interesting idea! I like the idea of more deeply integrating code agent with the terminal (e.g. shell, ptys, etc).

It's spawning PTYs but does it support SSH'ing into a remote session and running commands from a remote shell? That's something I built into zmx in order to scratch that "debugging in a remote VM" itch.

https://zmx.sh

another one: https://pico.sh

Nice! The entire https://pico.sh constellation of services are built off rss for notifications.

https://pico.sh/feeds is an ssh app that is an rss-to-email service.

It’s not. Node is part of the web ecosystem. Bun was a way to upsell paas

It wasn’t just on principle that those changes were rejected, they also stated the bun changes were not actually that great or general enough to upstream.

Neat! I'm curious, did you consider building on top of https://github.com/neurosnap/zmx which also does attach/detach and uses libghostty?

> 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...