Recent submissions

Comment · 3 days ago
You can clean it now and then, you know ;-)
Comment · 3 days ago
I have a Windows laptop with touchscreen and pen support and I like it (HP Omnibook, Lunar Lake). My top use case is probably holding the hinge of the laptop in a way that one thumb can reach the screen, and I scroll with it. Revolutionary I know! Sometimes reaching up and tapping a button (large target) is faster than using the touchpad. Signing documents with the pen. A 360° hinge helps, too, for tent mode and everything in between. Touch is easier on an airplane when space is tight for my arms.

I can and do live without it on other devices (my desktop PC), but it's a nice addition that should just be standard equipment everywhere.

Comment · 5 days ago
I am a nerd, but scrolling and my mouse cursor is obviously smoother at 120hz over 60. I can't tell the difference at 144 vs 120 however.
Comment · 11 days ago
Silly question, is PHP part of Project Glasswing? Crazy this has been dormant for a decade. And scary to wonder what else is lurking out there.
Comment · 29 days ago
Seems like it's good at reading German documents and reasoning over them. Custom German-language tokenizer, and one of the least hallucinating models.
Comment · 1 month ago
Open source? Neat idea.
Comment · 1 month ago
I use PI WEB (https://pi-web.dev, there's more than one with that name) to orchestrate remotely. Pi lets me run local models (currently Qwen 3.8 Flash Next on Strix Halo 128GB) and flagship models (with subscription auth, not API pricing) side by side. I typically ask GPT 6.1 Sol to review requirements and then spawn a subsession with Qwen, review Qwen's work, ask Qwen to fix. About 95% success with a single pass like that, achieving flagship quality without the price tag (albeit slower).

I started using Pi because it has a small system prompt and local models were too slow to start. Then I started adding custom skills and extensions when I hit little corner cases. It's been so easy to bend into what I need.

Comment · 2 months ago
I recently got a refurbished Strix Halo 128GB desktop for a steal ($2200) and I have a feeling it's going to be my last PC purchase for the next 3-5 years. Who knows how long this RAMpocalypse will last. My Lunar Lake 32GB laptop is already a couple years old, and it's not a speed demon but it ticks all the laptop boxes (portable, great battery).
Comment · 2 months ago
I for one prefer batteries-included. Decision fatigue for every cobbled together package takes its toll. Having a single, trustworthy, good-enough solution for so many things makes my life easier.
Comment · 2 months ago
I'm so excited about these two new models. Qwen 3.6 27B has been my sweet spot so I cannot wait to try 3.8. Glimmer looks really strong, I'm encouraged that Meta compared it to 3.6 in the model card! Exciting times!
Comment · 3 months ago
Strix Halo, 128GB RAM. I got a refurbished Corsair AI Workstation for a smoking price ($2100) about two months ago. Lucky timing that it was in stock.
Comment · 3 months ago
Wow, bike geometry is really good! Except for the missing wheels lol
Comment · 3 months ago
35B MoE is certainly a good and fast local model. I find 27B dense to be quite a bit smarter, so I daily drive that. I wish there was a ~100B MoE with maybe 10B active. It would be super smart and fast!
Comment · 3 months ago
Comment · 3 months ago
One of my mantras for decades has been: make change easy. Once you invest in great CI/CD, you can change stuff quickly and reliably. Then you can easily fix/roll back production issues. The dev team doesn't fear production deployments once change is easy.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton