News for hackers. Stuff that matters.
Re:Nvidia Was in Trouble Before the Jensen Huang Mess by caxap on Monday November 16, 2026 @01:33PM (#50521070)
As much as I love the idea of Taalas, their chatjimmy demo is a hard-wired (and probably very quantized) 8b LLM producing garbage extremely fast (17k tokens/s). Extrapolating from the picture of their PCIe board in their demo, I would expect a frontier model to require an IC not smaller than my desk.

At these dimensions, you are better off producing general-purpose inference ICs that can run any model, instead of baking in a single fixed LLM.

Re:Nvidia Was in Trouble Before the Jensen Huang Mess by FuriouslyAdrift on Monday November 16, 2026 @02:00PM (#50521455)
The long term target is JEPA-like primitives so models become irrelevant. You only have to accelerate critical paths to see massive gains.