News for hackers. Stuff that matters.

Risse

Re:Anthropic S-1 on Monday October 26, 2026 @10:10AM (#50244030)
24 GB 3090 user here. What is the best model for coding you have used? Qwen3.8 27B?
Same thing here in Finland, our website on WP Engine has been down for at least an hour now.
Re:ESP32S3 cluster running 1.58-bit (BitNet) Language model on Tuesday September 29, 2026 @04:10AM (#49889808)
Depends on what you consider to "usefully run LLMs".

Earlier this year, I bought a mini pc from Aliexpress, specs are roughly Ryzen H255, 24GB LPDDR5, 1TB SSD. This was around 350€ including VAT, customs, shipping etc. I would personally consider this somewhat of a lowest class of useful LLM box. It can run 8B models well, up to somewhere around 24B. I currently run Gemma 4 26B A4B Q5 on it, with MTP, and it is quite slow, but smaller models would run okay on it.

Somewhat of a verification, here's Mullvad's response to the post on Mastodon: https://mastodon.online/@mullvadnet/116822244689326681
They might be having some capacity issues, it was 404 for me for a while but now it's back.

Archive: https://web.archive.org/web/20260629105534/https://det.socia...

Re:Jolla phone – a full-stack European alternative on Monday March 02, 2026 @05:46AM (#47216235)
Check out this thread on Sailfish OS forums regarding EU Banking apps. I was surprised on how many actually work.

https://forum.sailfishos.org/t/banking-apps-on-sailfish-os/1...

Man, around 20 years ago, when I was a teenager, I used to noodle around AGS. I think I made a couple of "games", but never released them or anything. Glad to see it's still around!
Re:Cloudflare Stream + Backblaze vs. GCP for Short Form Video? on Wednesday December 24, 2025 @11:48AM (#46377104)
What's the software stack you have been using for the transcoding fleet? Is there any ready made open source solution?
Re:What I Learned About Deploying AV1 from Two Deployers on Sunday December 21, 2025 @01:35PM (#46347022)
I personally use av1an, and use VMAF target quality of 95 to 96. It's been really good and fast.

https://github.com/rust-av/Av1an

Re:Ask HN: What Are You Working On? (February 2025) on Monday February 24, 2025 @02:49AM (#43156834)
I've been dabbling with local ML projects, and trying to get them to run with ROCm on my Radeon 7900 XTX card. All the solutions to run for example Llama.cpp or Automatic1111 are a bit hacky, so I made a repo where I document how to run them in containers.

https://github.com/Krisseck/ROCm-Docker-Scripts

Needs more documentation and more projects, but all contributions are welcome!

Older »