Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU
Llama-modchip aims to run a 284-billion-parameter DeepSeek model using 64GB of RAM without a GPU. The provided information does not explain its technical approach. (github.com)
The headline and URL identify a story about The Diplomat retracting a report and acknowledging that an interview attributed to Newtype was fabricated. The headline frames the issue as connected to a diplomatic dispute and a South Korean startup’s AI testing in Ukraine, but the supplied text contains no account of the events, evidence behind the retraction, people involved, or consequences. It therefore establishes the apparent subject of the story without providing its substance.
The remaining text is a privacy-consent notice from Diplomat Media Inc. It asks permission to store or access device identifiers and browser details, and to use activity for personalized advertising, content, audience measurement, research, and product development. It also describes collecting precise location and scanning device characteristics. The notice says collected data may be shared with, stored by, or accessed by 1,753 partners for those purposes. Some partners rely on legitimate interest rather than consent; users can object to those activities, decline consent-based processing, and later change or withdraw their preferences through controls on the site.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
Llama-modchip aims to run a 284-billion-parameter DeepSeek model using 64GB of RAM without a GPU. The provided information does not explain its technical approach. (github.com)
A GNU maintainer’s controversial take prompted debate about AI-generated code in open-source projects. Commenters discussed project leaders who use AI tools while distancing themselves from code ownership. (social.treehouse.systems)
ThinkStream says AI can generate work, but people still need to understand it. The provided page content contains only an anti-bot prompt. (thinkstream.app)
Ensemble is a book and open-source project for building an AI coding agent that helps create the next edition. It advocates development-driven specifications, where specs evolve alongside implementation instead of dictating development upfront. (github.com)
Maple uses manifold-activated pruning to compress mixture-of-experts language models below 2 bits per weight. Its developers say it runs Gemma 4 26B at 45 tokens per second on a 6GB GPU. (github.com)
A longtime Claude Code user is switching to Pi after growing frustrated with incompatible instruction-file formats, limited VSCode session support, and bugs in the GUI extension. They say Claude Code has prioritized adding features over fixing reliability and usability problems. (caleb.software)
Today's best Hacker News stories, summarized and screenshotted, one email a day.