A smart performant local model will be the equivalent of having good anti-virus and firewall software. It will be the only thing between you and wrong prompts being sent every which way from which app.
We’re probably three or four years away from the hardware necessary for this (NPUs in every computer).
A local LLM wouldn’t have helped at all here.
You can’t imagine a MITM LLM that sits between you and the world?
Local llms can get offline searched for vulnerabilities using gradient based attacks. they will always be very easy to prompt inject.
I can't imagine how such a thing would _help_, it seems like it would just be another injection target.