OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about “the Hugging Face Incident” (previously on this blog). The video was published yesterday. It’s short and information …
I haven’t found time to watch the OpenAI presentation yet, but this timeline is a nice quick summary.
This is one of those things that should, in a rational world, make people realize that these models are not under control.
which is why I have a sandboxed environment that’s firewalled off my normal network and only allows things in.
only thing I could do better is to either vlan it or airgap it.