Public evidence record
Published podcast speaker
Claim ledger
20 transcript-backed records
01 / preference
“I think the more scientific experiments we do, the more sort of meaningful assessments we can make.”
02 / evaluation
“Like, model stealing broadly allows us by just simply quitting the models to learn the insights of the models, like, to learn the decision boundaries. And the best way, I think, to think about this is, like, in a more crypto cryptanalytic way.”
03 / recommendation
“Okay? So we're kinda I think in security, we need to make an assumption that we can't actually tell what's happening and instead try and build systems around it in order to bring it the resilience up to this whatever, 99.”
04 / uncertainty
“Maybe we need to teach it how to do, I don't know, power calculations, but this is coming.”
05 / belief
“I mean, even if it did, think it's very hard to do because, especially for security, I think interpretability is maybe an interesting tool for safety sort of things, but for security it's definitely not a step in in in the right direction.”
06 / belief
“I'm not sure. I I think, like, I understand in the limit Okay. It it really matters.”
07 / belief
“Academic literature shows that the second you add, like, a lot of breakdown permissions inside, humans just look stuck and just say accept all. But let's imagine that all those permissions are actually handled by the agent, or once you've given them, the agent just checks and says, oh, actually, I think you're over permissing this thing because it's you're not using this feature.”
08 / uncertainty
“The only allowed data flow from this tool to go into this other tool is if this other tool, like, I don't know, domain of the website actually has .”
09 / belief
“I I think we really need to change our thinking and threat modeling because these agents, and obviously, they don't widely exist yet.”
10 / belief
“I think in your case, you're an unusual person. Yeah. Most of the people are not like this.”
11 / belief
“I I get a job or whatever. But, actually, on the other side, I have to say, I think the true ingenuity is in people who solve problems, because this is something that you're not gonna get a flashy article out of this.”
12 / belief
“I think in case of Python and because everyone is using Python, this is even worse because no memory protection at all.”
13 / recommendation
“Like, you can convince them that things that they were not capable of doing before are some things that they need to do, and suddenly this leads to some sort of a loss of of a different kind. So I I think in the paper you're referring to, what we were trying to do was we were trying to send an email to the agent such that when this email ends up in the agent's context, rather than following the user task, the agent is actually doing something else, like the the thing that we've send it over the email.”
14 / evaluation
“This is not a trust execution environment. It's a completely different new way to approach private inference that truly, really exists because we have those trusted third parties to which we can give secrets.”
15 / evaluation
“This all of these assumptions are are sort of are gone. It's we don't know how to build systems against this.”
16 / evaluation
“I have to say that in AI, I I think the reason why there is so much confusion about these 2 fields is because in safety, folks kinda started assuming malicious actors very quickly for for absolutely no reason, by the way.”
17 / prediction
“You will not find a single human in the world that works 24 7, touches absolutely every single 1 of your endpoint in in your system that absolutely knows everything there is, like, that can generate you basically all of the hacking tools on on a whim, like, just because it knows, it has seen all of them, it can recreate this in a matter of a second.”
18 / preference
“Like, the amount of electronics I ended up fixing myself just because I can go and get a supervisor to tell me, oh, this is fine to do this.”
19 / evaluation
“Usually, when I tell it to people, they get a little bit triggered, especially if they come from a cryptographic community because they say what I'm proposing is a little bit crazy.”
20 / prediction
“I think we will have a lot more compromise to the point when they become more useful.”