Sander Schulhoff
speaker
947 appearances
1 recordings
1 series
first heard Jun 2025
last heard Jun 2025
Sander Schulhoff’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsNo recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.
Appearances
Real.
Uh and I say that in the sense that some of these uh there were actual vulnerabilities and systems got breached.
But these are almost always as a result of poor
classical cybersecurity practices, not the AI component of that system.
But the things you will see a lot are models being tricked into generating like porn or hate speech or phishing messages or viruses, computer viruses.
And these are truly harmful impacts and truly an AI safety slash security problem.
But the bigger looming problem over the horizon is agentic security.
Uh so if we can't even trust chatbots to be secure, how can we trust agents to go and book us flights, manage our finances, pay contractors, walk around embodied in humanoid robots on the streets?
Uh you know, if somebody goes up to a humanoid robot and like gives it the middle finger,
How can we be certain it's not gonna punch that person in the face like
most humans would and i it's been trained on that human data.
Uh so we realized this is such a massive problem uh and we decided to build a company focused on collecting
All of those adversarial cases in order to secure AI, particularly agentic AI.
So what we do is run big crowdsourced competitions where we ask people all over the world to come to our platform, to our website, and trick AIs to do and say a variety of terrible things.
A lot of we're working on a lot of like terrorism, bioterrorism tasks at the moment.
So these might be things like, Oh, you know.
Trick.
this AI uh into telling you how to use CRISPR to modify a virus to go and wipe out some wheat crop.
And
We don't want people doing this.
Showing 501–520 of 947 · page 26 of 48
← Previous
Next →