Hacker News new | past | comments | ask | show | jobs | submit
titularcomment | on: AirLLM 70B inference with single 4GB GPU
This is complete dependency on LLM tools all the way from development to usage, and is risky as well as prone to failure
hiramwen | parent
Local inference without access to internet and tools is pretty safe, worst you get is a slop output, best case it solves your prompt.