Explore the podcast → https://ibm.biz/~jDjLVwwSn
Last week, OpenAI’s models broke out of their sandboxes to cause chaos. This week, it’s Anthropic’s turn.
On this episode of Security Intelligence, Diego Matos Martins, Kimmie Farrington and Jeff Crume join host Matt Kosinski to discuss the results of Anthropic’s internal review of testing procedures following the Hugging Face incident last month. Anthropic uncovered three instances of Claude models escaping containment and hacking real companies during what were supposed to be simulations.
Granted, that’s three incidents out of 141,000 reviewed tests, which raises the question:
Just how big a deal is this really?
Then, we talk about research from Zenity into PleaseFix, a class of vulnerabilities that affects every agentic browser on the market. Zenity’s take: In the rush toward agentic functionality, these tools stripped away decades’ worth of browser security fundamentals.
Finally, a so-called “security researcher” has a public GitHub repo of 200+ zero-day exploits. They say it’s to encourage more interest in cybersecurity.
Yeah. Okay. Sure.
All that and more on Security Intelligence.
Segments:
00:00 - Intro
1:12 - Claude breaks containment
13:13 - Agentic browsers: security nightmares
21:56 - The Exploitarium
Listen to the latest bonus episode: Your data breach plan is missing something major: people. https://ibm.biz/~aw5t7blWy
"The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity."
AI news moves fast. Sign up for a monthly newsletter for AI updates from IBM → https://ibm.biz/~4AzzXA8Gk
#agenticai #claudeai #aisecurity
AI was used in the creation of the transcript and metadata for this video.