02 / recommendation

4 Oct 2025

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.

“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.”

Speaker: Ilia Shumailov
Episode: AI Agents Can Code 10,000 Lines of Hacking Tools In Seconds - Dr. Ilia Shumailov (ex-GDM)
Publisher: Machine Learning Street Talk

Ilia Shumailov

What Ilia said.

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.