News for hackers. Stuff that matters.
Re:OpenAI closes its monster $10B funding round at $27B-29B ... by jimkoen on Saturday April 29, 2023 @09:48AM (#35752832)
Because GPU-Servers that can run a typical LLM are less than 5k, which includes installation. Really, running an LLM seems to be no more complicated than running a NAS from a system administrators perspective.

Emphasis on running, not training.

Re:OpenAI closes its monster $10B funding round at $27B-29B ... by MichaelZuo on Monday May 01, 2023 @02:49PM (#35777330)
5k can't even get you 80 GB of VRAM on a GPU. How is that possible?