Superhuman AI Exfiltrates Emails
promptarmor.com
promptarmor.com
There are countless examples of schemes in stories where codes and cryptography are used to exfiltrate information and evade detection, and these models are trained on every last piece of technical, practical text humanity has produced on the subject. All they have to do is contextualize what's likely being done to check and mash together two or three systems it thinks is likely to go under the radar.
Browsing the web is both communication and untrusted data, so it must never have access to any trusted data if it has the ability to browse the web.
The problem is, so much of what people want from these things involves having all three.
Pretty much. Also there's no way of "securing" LLMs without destroying the quality that makes them interesting and useful in the first place.
I'm putting "securing" in scare quotes because IMO it's fool's errand to even try - LLMs are fundamentally not securable like regular, narrow-purpose software, and should not be treated as such.
Indeed. Between this fundamental unsecurability and alignment, I struggle to see how OpenAI/Anthropic/etc will manage to give their investors enough RoI to justify the investment
As Claude Code increasingly uses browser tools, we may need to move away from .env files to something encrypted, kind of like rails credentials, but without the secret key in the .env
So perhaps they should be.
> and can't be.
Ah but they must, because there's not much else you can do.
You can't secure LLMs like they were just regular, narrow-purpose software, because they aren't. They're by nature more like little people on a chip (this is an explicit design goal) - and need to be treated accordingly.
Unless both the legalities and technology radically change they will not be. And the companies building them will not take on the burden since the technology has proved to be so unpredictable (partially by design) and unsafe.
> designed to be more like little people on a chip - and need to be treated accordingly
Deeply unpredictable and unsafe people on a chip, so not the sort that I generally want to trust secrets with.
I don't think it's that complex, you can have secure systems or you can have current gen LLMs. You can't have both in the same place.
Very true when comparing to acquaintances, but at a scale of any company or system except the tiniest ones, you can't blindly trust people in general either. Building systems involving people and LLMs is pretty similar.
> I don't think it's that complex, you can have secure systems or you can have current gen LLMs. You can't have both in the same place.
That is, indeed, the key. My point is that, unlike the popular opinion in threads like this, it does not follow that we need to give up on LLMs, or that we need to fix the security issues. The former is undesirable, the latter is fundamentally impossible.
What we need is what we've been doing ever since civilization took shape, ever since we've started building machines: recognize that automatons and people are different kinds of components, with different reliability and security characteristics. You can't blindly substitute one for the other, but there are ways to make them work together. Most systems we've created are of that nature.
What people still get wrong is treating LLMs as "automatons" components. They're not, they're "people" components.
I think LLMs are to be treated as something completely separate from both predictable machines ("automatons") and people. They have separate concerns and fitness for a use-case than both existing categories.
How would you apply the threat of those to "little people on a chip", exactly?
Imagine if any time you hired someone there was a risk that they'd try to steal everything they could from your company and then disappear forever with you having no way to hold them to account? You'd probably stop hiring people you didn't already deeply trust!
Strict liability for LLM service providers? Well, that's gonna be a non-starter unless there's a lot of MAJOR issues caused by LLMs (look at how little we care about identity theft and financial fraud currently).
Doesn't help in the case where the LLM is processing actually sensitive data, ofc.
So for you to successfully use my DNA as code, without also borrowing the compiler from my body, would be a major scientific result, shining light on the questions outlined above.
So in short: I'm happy to contribute my DNA if you cite me as co-author on the resulting paper :P.