SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist
Security Now (Audio)Show Notes
Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are.
Understanding the controversy surrounding "AI Model Distillation"
Anthropic moves to make their most powerful Mythos 5 model more widely available.
Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
The astounding and disturbing truth about the way conversation AI actually works
Show Notes - https://www.grc.com/sn/SN-1093-Notes.pdf
Hosts: Steve Gibson and Leo Laporte
Download or subscribe to Security Now at https://twit.tv/shows/security-now.
You can submit a question to Security Now at the GRC Feedback Page.
For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.
Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit
Sponsors: threatlocker.com/twit
box.com/AI
hoxhunt.com/securitynow
guardsquare.com
material.security
More from Security Now (Audio)
An unreleased AI solved a 26-year-old cryptographic secret in less than half an hour, exposing the origins of a widely used standard. Discover what this jaw-dropping breakthrough means for the future of trust and transparency in cybersecurity.
Think your open-source AI model is safe? This episode uncovers how LLMs can be secretly booby-trapped with undetectable backdoors, raising the stakes for anyone deploying AI in serious environments.
As AI becomes startlingly capable, top minds at OpenAI admit they can't always control what their own creations do—or even fully understand how they think. This episode dives into the real-world tension between rapid progress and the growing challenge of keeping AI truly aligned.
With millions racing to embrace AI assistants and cybercriminals pivoting to new, high-stakes tactics, the episode tackles the dizzying pace of change and asks: just how worried should we be? The discussion pulls back the curtain on AI's unpredictable power, the escalation of digital extortion, and why the next breach may hit closer to home than you think.
After Microsoft's historic Mega Patch Tuesday, enterprise IT teams worldwide are scrambling as a wave of updates triggers system meltdowns, broken domains, and silent Excel failures. Find out how AI-driven speed collided with real-world chaos.