Latest / Logosofia no Dia a Dia
Why Agentic AI Needs More VRAM Than You Think
When your AI model tries to debug and test code autonomously, it demands massive memory. Herman and Corn explore why 12GB of VRAM isn't enough, and how to build a local inference server that actually keeps up. Episode 110 — myweirdprompts.com/n/110 (permanent short link: myweirdprompts.com/462032)
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.