News for hackers. Stuff that matters.
Re:Tongyi DeepResearch – open-source 30B MoE Model that riva... by kmarc on Sunday November 02, 2025 @04:13PM (#45793505)
I caught myself that most of my LLM usage is like this:

ask a loaded, "filter question" I more or less know the answer for, and mostly skip the prose and get to the links to its sources.

Re:Tongyi DeepResearch – open-source 30B MoE Model that riva... by ukuina on Monday November 03, 2025 @07:01AM (#45798160)
The "loaded question" approach works for getting MUCH better pro/con lists, too, in general, across all LLMs.