Hacker News Reader

v3ss0non Self-hosted HTTP tunnels with SSH and Nginx

Just install pangolin and call it a day

v3ss0non Alternatives to MinIO for single-node local S3

This need to go mainstream.

v3ss0non Inside ZCode: Silently uploading your Git history to the cloud

I do used vim for many years too , but when developing web apps , Terminal become a limitation , things cannot be preview outright in the interface is a big downer.

Huge plus for GUI base dapplicaitons : you can view total and complete render of HTML , PNG , SVG , PDF right in the IDE/Harness tools. That is no where terminal app can do with good performance .

v3ss0non Code Scans

which ai come up with that buzzword lol

v3ss0non Inside ZCode: Silently uploading your Git history to the cloud

looks cool would be nice if its GUI , terminal have limitations .

v3ss0non Inside ZCode: Silently uploading your Git history to the cloud

Never use a Harness if it is not opensourced.

DeepSeek Harness is my favorite for coding. Hermes is my favourite for Other things , followed by OpenCode (sucks at managing long running services) .

Others swear by Pi.dev

v3ss0non Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

On actual agentic task , it just fail.

v3ss0non Code Scans

just another prompt right?

v3ss0non Alternatives to MinIO for single-node local S3

I heard good news about SeaweedFS

v3ss0non Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

Bot? Care to explain any difference vs DSH / OpenCode / Hermes ?

v3ss0non Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

> I'd need a whole rack of GPUs

no , all you need is one small DGXSPark with proper setup.

v3ss0non Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

Deepseek 4 flash can run locally , and qwen 3.8-next-flash , they are already gpt 5.6 tier.

v3ss0non Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

You haven't tried DeekSeek v4 or GLM 5.3 or Qwen 3.8 Next?

You are missing out a lot.

Try that with Hermes or Opencode or Deekseek Harness , even Qwen 3.8 27b works really well for that kind of that.

I just ask it to install windows as a vm on my linux and install vs Community 2019 on it , and then build a legacy vb 2019 project on it. and sleep

When i wake up :

It installs Qemu , setup a vm , inside vm download and install windows 10 on its own , clicking next next next as needed , typing in things , writing powershell , python scripts , that run automatically after install by baking into CD that includes ssh server , reboot , it logins into ssh , trigger pythons script that continue installation of vs 2019 community , which includes a driver that click the installation steps , installs nuget , install all depedencies and then build the project into exe after i woke up.

That is with 100% pure local AI .

v3ss0non Show HN: Sunk Cost – How long until a local LLM rig pays for itself?

Besides from privacy: I already making twice now.you own the hardware and the price had doubled since i bought. Almost tripled. You missed the opportunity and i have 4 of those awesome machines. Cry on.

I sell those to business who need local air gapped requirments and I make a lot more money!

I can run the alliterated models where none of the service prvoider even dare to provide.

THose benefits outweights a few K.

And show me an api provider that allows me to run 10x agents concurrently for 5 days straights .

v3ss0non Mistral raises €3B

Thats one of the valid point.

v3ss0non Mistral raises €3B

No amount of $ would improve mistral if they cant fix fundamental flaws. They aren't even on par with chinese models a year ago.

v3ss0non Xwayland 26.1.0 rc1

who care about political affiliation when software is done right? Opensource is Political neutral.

v3ss0non Xwayland 26.1.0 rc1

Wayland should expired, Wayland is architectural failure plagued with bad design decisions, xlibre is gaining momentum and it is not broken piece of a pile

v3ss0non Mistral OCR 4.1

Are you serious? Tasserect is the worst compare to PaddleOCR , Surya/Marker

v3ss0non Mistral OCR 4.1

Gemini is best at OCR and document extraction so far. We had tested for insurance needs. None match Gemini even flash level yet.

v3ss0non Gemini 3.7 Flash

GEMMA 4.5 gogoogogo

v3ss0non DeepSeek V4 Pro 0813

I do that kind of things all the time with Qwen 3.5 122B. It works well in one shot with Cline or Opencode.

May be your harness problem?

v3ss0non Delta

Zed in Identity crisis.

v3ss0non EYG: A Programming Language for Humans

why this why we have llms? thats totally usless. I think all new programming langugaes are ueless right now with advancement of LLMs.

v3ss0non Ziggity – A terminal UI for Git, written in Zig

Lazy in a way that it was been vibe coded

v3ss0non Ziggity – A terminal UI for Git, written in Zig

You beat me to it

v3ss0non Hyprland 0.55 announced the switch to Lua for its config files

That's why I love qtile, written in python, modify everything in python, can import any module of it and can install anything, extend existing layout without forking to support very interesting and customized WM layouts, all entirely in python, call any python code in WM.

v3ss0non Biggest Probabilistic Computer Turns Noise into Answers

Best LLM ever.

v3ss0non A native graphical shell for SSH

Exactly - and all the best UX Decision are outdated as F - where the rest of the world consider those UI/UX Smells.

v3ss0non A native graphical shell for SSH

I never liked TUIs. Proper GUI , even Electron based apps are far superior than TUI , it just need to be built properly. But bad GUI is a bad GUI. This have all the UI/UX smells.