Post

As someone who has been experimenting with running local models on GPU-less Raspberry Pi’s lately, can confirm—even smaller models that are ostensibly optimized for limited hardware environments are pretty near unusable.

cpu is dogshit slow for inference, and self-replicating worms already exist (you may know them as rVPNs or botnets) alas they're just repackaging an existing problem as "you should be afraid of everyone's ai except ours"

0 reposts4 likes