Why AI Security Threats May Require a New Defense Model

I don't even know what a dramatic enough word to use, but the problem coming

towards us, um, I think is still

something that we have not as organizational leaders or countries or

individuals taken seriously. Uh, there was like a moment

earlier this year where

it was like the Mythos freak out or whatever people called it,

and I think things

did get somewhat better.

Like, people definitely patched some bugs.

But it was another one of these cases where people didn't really intuit the

exponential. So it's like, okay, there are these models.

They can find a bunch of security vulnerabilities.

Those are probably all of the security vu- vulnerabilities that exist or all the

security vulnerabilities that models are ever gonna find.

And I don't think most people sort of said, "Okay, the models are gonna get

much smarter. They can probably find bugs, like crazy bugs, you know,

bugs that are outside of the normal threat model

of what we think a hacker can do." Um, you know, hardware level,

insane stuff, whatever. And so people

fixed some bugs

and, you know, security professionals still freaking out,

CISOs still freaking out.

But largely speaking, I think most organizational leaders have

somewhat moved

on.

And

the models have kept going.

And I, I no longer think we're gonna be able to

just patch all the bugs.

I think we're gonna have to completely switch the defense model to sort of using

the same technology to, for sort of a new kind of defense shield.

And I think it's a huge safety and security issue