LLMs Are Complicated Now
(news.ycombinator.com)
1.
2.
3.
4.
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
(news.ycombinator.com)
5.
Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
(news.ycombinator.com)
6.
7.
Flash-MoE: Running a 397B Parameter Model on a Laptop
(news.ycombinator.com)