Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A desktop made for one

isene.org

Post reply on HN
Print view View original

271–280 of 281 posts

Re: A desktop made for one

#271

Post by Ygg2 »

utopiah wrote: post #225
Ygg2 wrote: post #223

Earlier quoted context omitted.

> Your software can be made by you, for you. Yeah, but it's probably derived from OSS software anyway either via license or LLM. That said, you can customize your Linux/BSD/Haiku/TempleOS as much as you want. But consider the following: even in the better case of an OS making 1% of OS userbase (vs. 0.0000001%) no one wants to support it. Want to play Diablo? Better to sit down and waste your time.

That's the beauty of containers, virtual machines like QEMU or compatibility layers like Wine/Proton. As long as your super esoteric software implements the interfaces those rely on, you are able to run everything else.

No one will support Windows if no one uses it either.

Re: A desktop made for one

#272

Post by adampac »

furyofantares wrote: post #107

I've got a wrapper around tmux for an audience of one. I can operate claude code, codex, opencode, or just a shell, from any of my devices to any of my devices (via tailscale) or more commonly, operate it on my exe.dev server. I often continue a session on my phone, sometimes with voice. I have buttons for viewing files or following links the agent has referenced, extracted from the stream of text, and I have some bu…

Would love to learn more about your setup as I put something fairly similar for myself and looking for ways to improve it even further.

My goal is to have agents work independently from any of my devices (hence VM setup) and to access any session at any time.

My setup so far:

A simple VM on Google Cloud. Always on. Repo lives in there. Claude Code, Codex, Gemini installed as CLIs.

The agents run inside terminal sessions on the VM, managed by zmx (small Zig project, keeps a raw PTY around). Session keeps running regardless of what’s connected.

From the Mac, transport is Eternal Terminal on port 2022. ET is like SSH but reconnects silently. I never see the disconnect.

From the phone, transport is mosh. UDP based, roams gracefully (cellular to wifi and back). Client is Moshi (iOS), renders the terminal and manages tmux sessions well. Moshi needs alternate screen for scrollback, so on the phone path zmx is wrapped in tmux. The tmux is just an adapter for the phone client, not the persistence layer.

The point: both transports attach to the same zmx session. Same scrollback, same prompt, same agent state. Laptop, phone, both at once, all clients of the same long running shell on the VM.

The annoying part was scrollback: duplicated history, lack of native scroll, lagging. zmx avoids the alternate screen (tmux uses it by default, which makes scrolling agent output awkward). Combined with Claude’s --no-flicker flag, the terminal’s own scrollback ends up actually usable.

I wanted to avoid manually switching scroll modes and re-attaching. Moshi sees all my current sessions on the Mac, I just tap and swipe between them. Awesome.

A few shell functions hide the layering on the Mac with a few commands and keyboard shortcuts.

Re: A desktop made for one

#273

Post by wyre »

techgnosis wrote: post #257
wyre wrote: post #106

Great job! This is super cool and probably feels incredibly satisfying! I do find it curious how even after replacing all of your software, but are still using Claude Code instead of building your own coding agent.

Can't use his Max sub with his own custom agent. No custom agent is worth per-token Opus pricing

As someone who did write their own custom agent, I figured that was the reason.

However, gpt5.5 does not make me miss Opus.

Re: A desktop made for one

#274

Post by cestith »

i_think_so wrote: post #270
cestith wrote: post #267

Earlier quoted context omitted.

Why wouldn’t he use an agent to find the weakness? How would he know what language is on the backend of a web service without already having infiltrated the server? If he’s in the NSA, why wouldn’t he just sneak a vulnerability into common PHP, Nim, or Rust libraries the site is likely to use?

Bro. Come on. Don't overthink it. I wasn't trying to write a Great American [Cyber]Spy Novel. I banged out a silly short story over maybe 40 minutes while I was eating. Then I went back and cleaned up a bit of the text I didn't like and gave it to the world. I smiled and chuckled a few times as I was writing, because that's what often happens when an author is making something he's happy with. I hoped a few others wo…

I’m one of your upvoters. Just making some notes. It’s good fiction, and most fiction has holes when people in the field involved look closely. That’s not a dig at it. I enjoyed reading it enough to engage.

Re: A desktop made for one

#275

Post by vidarh »

alchemist1e9 wrote: post #207
geir_isene wrote: post #176

For those who may be interested - I broke down some numbers for my CHasm and Fe2O3 efforts in a new blog post: https://isene.org/2026/05/Audience-of-One-Numbers.html

You’ve reduce the memory requirements so much that it could all run on an early 90s computer easily. When I see such extreme examples I think back to the OLPC machines and this idea of how can extremely cheap but with useful software computers be available in very impoverished areas. I understand this has nothing to do with your argument or anything you’re writing about. It just made me think if LLM assisted software…

Back when I was using Amiga, there was an ongoing competition to trim tools down to the point you'd see people shaving off bytes at a time in some cases. It largely stopped because of the time investment. Ironically, if we can fire off some hugely resource hungry LLMs and trim the bloat we might end up reducing the resource requirements for everything else again...

Re: A desktop made for one

#276

Post by tmzt »

I'm working on this too. I'm building a distributed environment where compute and GPU resources can be on one system, display on another, organized into a type of piconet. So far, I'm working with offline/local AI though running into limitations with it. The goal is to allow for a user to customize the environment with personalized cards powered by open schema databases. The same UI works on mobile devices, tablets, desktops, even TVs and IoT devices (ESP).

Re: A desktop made for one

#278

Post by onetom »

utopiah wrote: post #240
customguy wrote: post #235

Earlier quoted context omitted.

To me this doesn't seem like a step towards those foundations, but another layer of of loss of agency. You can run "a" model locally, but you cannot make it locally (at least not for the purpose of just talking software into existence). You need to slurp up all the internet first, so to speak. And even if you could do that, you still depend on people putting new things onto the internet for you to slurp up. So is it…

Agreed, I wasn't advocating on using LLMs, even "open" or "local" ones.

i think "self-hosted", "home" or "company"/"office" should be the term we use, instead of "local", since

1. every LLM is _local_ in relation to the location the storage and/or the computers hosting/using it

2. the LLM running in your home is only _local_, until u step out of the door, but if you have some tailscale or zerotier VPN setup, u can still access it _remote_ly...

Re: A desktop made for one

#280

Post by computably »

i_think_so wrote: post #241
gwern wrote: post #112

Earlier quoted context omitted.

But doesn't that make it bad? It doesn't say anything new. Unlike the software in question, which is personalized, so it's not even symbolically reflecting the topic. It's a sheer waste of pixels and time spent looking at it or scrolling past the cognitive junk food.

Come on, bro. Why you gotta be like that? I mean, I'm a gwern fan, but...can't you just let people enjoy things?

> can't you just let people enjoy things?

Dumping slop into the public commons deserves criticism.

Post reply on HN