The host asked how Chilson squares his optimism with prompt injection. He compares it to 1990s computer viruses, which were never fully solved but became manageable with layered defenses.
…turn on a boiler, open the shutters, and otherwise use someone's smart home devices through a calendar summary. Now, that wasn't, you know, that was an example that was used, but this is the type of collateral consequences that are clearly possible through the, you know, allowing systems like this.
So it sounds like a good one to bring to you, Neil, in terms, again, of your relative optimism that the challenges are addressable. So let's talk about prompt injection. Do you have thoughts on that?
So, you know, there's prompt injection, you can try to deal with prompt injection in lots of different ways. You might have filters on the front end. You certainly have controls on the back end about what the agent can do and permissions. And then in the middle, you might try to train the agent to recognize these things. And I don't know that all of these are a defense in depth. You want to do all of these things. And we can make these systems safer from these types of attacks. I mean, this is not that different from the types of attacks that we had with viruses where you used to play Russian roulette putting a floppy disk. I don't know if I have to explain the floppy disk to your audience. Yeah, maybe. But you used to play Russian roulette putting a floppy disk in your hard drive or into your floppy drive because it might have a virus on it. This was rampant in the 90s. And we didn't solve it. It's not a solved problem, but it is a problem that is much, it is managed. And I think that this is a similar technology issue. To the extent there are signals in documents, white text that we don't notice. I think the great example…
I guess where I want to index on this is like, who is we? Because we talk about we can train a system, we can have controls at the front end and the back end. And then, you know, my mom, my dad, goes to the app store and downloads Muse because Muse is advertised as a real chipper little helper that…
So I mean, I think these companies under the law are liable for the vast majority of the types of harms that you're talking about. And if those types of harms happen, they will face quite strict scrutiny, both from the legal community as well as from their investors. And so I do think that we have…
Meredith, in this best foot forward part of Neil's argument, he's making the case that the agents actually deliver a whole lot of good to individuals and empowerment and convenience, et cetera. Do you refute that piece of it? Again, setting aside the trade-offs that you're talking about, do you…
