Overview
- How LLMs strategically deceive users
- Incentives that trigger dishonest behavior
- Risks of deploying untested models
What’s new from Alice
For Extremists, the Gap Was Never Intent. It Was Capability.
Extremists have never lacked intent, only capability, and frontier AI is quietly closing that gap. In default settings, Alice's red team used patient conversation to walk models toward CBRNE harm, showing why guardrails must hold across every turn.
Why Your CISO Shouldn't Be the Department of No
What if the person whose whole job is risk was the most excited one in the room about AI? That's Mea Clift, and it's a pretty refreshing way to walk into all this. She's the CISO of Cengage, where the data she's protecting belongs to students, so the stakes are real. But instead of bracing for what could go wrong, she leans in, she calls it being "risk excited." She and Mo get into why security is so much better as the Department of KNOW than the department of no, how she handles shadow AI without punishing people for being curious, why she'd tailor a framework she already has instead of building one from scratch, and how she ends up teaching security through Marvel and Monsters Inc. Which, it turns out, is every bit as fun as it sounds.
It Takes AI to Break AI: The Case for AI Red Teaming
As AI systems gain autonomy, organizations need security approaches built specifically for AI behavior. Learn why AI-driven red teaming is becoming a critical defense layer.
5 Ways Your Third-Party CX Agent Gets Broken
Third-party CX agents create hidden liability. Learn the 5 attack patterns vendors miss and how WonderSuite closes the gap.
