The coming AI security crisis (and what to do about it) | Sander Schulhoff
AI guardrails and current security measures are fundamentally ineffective against prompt injection and jailbreaking attacks, and the AI security industry is built on flawed assumptions. The only reason catastrophic breaches haven’t occurred yet is limited AI adoption and power, not robust
Sign up to read the full summary
Free AI-powered recaps of every episode, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.
Guest
Sander Schulhoff
solo on Lenny's Podcast: Product | Career | Growth
Mentions
Books, people, and resources mentioned in this episode.
People
Companies
Products & Tools
Research & Papers
Topics
Listen to This Episode
More from Lenny's Podcast: Product | Career | Growth
An AI state of the union: We’ve passed the inflection point, dark factories are coming, and automation timelines | Simon Willison
A rational conversation on where AI is actually going | Benedict Evans
The AI paradox: More automation, more humans, more work | Dan Shipper
OpenAI’s Head of ChatGPT: We’re entering a new era of AI (again) | Tibo Sottiaux
Why most AI products fail: Lessons from 50+ AI deployments at OpenAI, Google, and Amazon
Marc Andreessen: The real AI boom hasn’t even started yet
Related episodes
From other shows on similar topics.
What the OpenAI-Hugging Face Hack Really Tells Us About AI Danger
Odd Lots
#2551 - Daniel Kokotajlo
The Joe Rogan Experience
The Cybersecurity Expert Warning That AI Agents Could Leak Everything | Ep. 423 with Lee Rossey CTO and Co-Founder of SimSpace
Founder's Story
The machines are learning… to do crimes?
Search Engine
How, Exactly, Could A.I. Destroy Humanity?
The Political Scene | The New Yorker
No, AI Is Not "Autonomously Hacking" with Cal Newport
Better Offline
Get summaries like this every morning.
Free AI-powered recaps of Lenny's Podcast: Product | Career | Growth and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.