Hacker News Reader

I tested it with the DGX Spark in my home-lab and it works well; however, for agentic tasks, I didn't get output as optimal (in terms of speed/quality) as I did with Nemotron. Also ref: https://developer.nvidia.com/blog/run-local-agentic-ai-workf...

Discussion: https://news.ycombinator.com/item?id=49615537

Thanks! Just shared my thoughts

> People can change access or disconnect a service whenever they want. People can also opt out of their interactions being used to train Meta’s AI models.

-- https://about.fb.com/news/2026/09/introducing-muse-personal-...

The last not mean the least!

Meta Just Launched Muse