SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails

Security Now (Video HD) by Leo Laporte

Aug 18, 20262:49:05Technology

From autocorrect to full-fledged conversationalists, discover how a few tweaks transformed language models—and why understanding this shift exposes urgent questions about AI safety and control. Trusting an open source AI...

Related Episodes

Continue listening to more episodes from Security Now (Video HD).

SN 1097: Mega Patch Tuesday Fallout - When AI Outsmarts Its Makers

Sep 22, 2026 - 2:50:02

After Microsoft's historic Mega Patch Tuesday, enterprise IT teams worldwide are scrambling as a wave of...

SN 1096: Are we the Krell? - 153 Million Driver's Licenses Leaked

Sep 15, 2026 - 2:50:47

Are we charging toward a Krell-style catastrophe with AI, arming ourselves with incomprehensible power wh...

SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race

Sep 8, 2026 - 3:06:06

OpenAI's latest advances have the rumor mill buzzing about "hidden thoughts" and unsupervisable models, b...

SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?

Sep 1, 2026 - 2:51:59

AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critic...

SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist

Aug 25, 2026 - 2:48:10

Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt...

SN 1091: The Post BlackHat State of AI - When AI Writes Malware

Aug 11, 2026 - 2:51:12

AI agents are breaking free from their test environments, outsmarting their creators and breaching real-w...

SN 1090: Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming

Aug 5, 2026 - 2:05:11

At Black Hat Las Vegas, the Security Now crew digs into how AI is not just finding hidden software bugs b...

SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines

Jul 28, 2026 - 3:07:56

What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-wo...