World Model · podcast knowledge graph

The coming AI security crisis (and what to do about it) | Sander Schulhoff

2025-12-21 · 93 min · 50 entities

episode page audio

Asserted relationships

  • → references Sander Schulhoff person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://linkedin.com/in/sander-schulhoff
  • → references The Ai Security Industry Is Bullshit website
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.substack.com/p/the-ai-security-industry-is-bullshit
  • → references Las Vegas Cybertruck Explosion person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/2025_Las_Vegas_Cybertruck_explosion
  • → references @Matsresearch website
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://substack.com/@matsresearch
  • → references CBRN Defense person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/CBRN_defense
  • → hosted by Lenny Rachitsky person
    0.55
    evidence rules-v4
    Feed author/publisher: Lenny Rachitsky
  • → discusses Technology company
    0.40
    evidence rules-v4
    Feed category: Technology
  • → discusses Business concept
    0.40
    evidence rules-v4
    Feed category: Business
  • → discusses Entrepreneurship concept
    0.40
    evidence rules-v4
    Feed category: Entrepreneurship
  • → references penname.co website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://penname.co/
  • → references openai.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://openai.com/
  • → references Prompt Report book
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://learnprompting.org/blog/the_prompt_report?srsltid=AfmBOoo7CRNNCtavzhyLbCMxc0LDmkSUakJ4P8XBaITbE6GXL1i2SvA0
  • → references simonwillison.net website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/
  • → references servicenow.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://servicenow.com/
  • → references metronome.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://metronome.com/
  • → references sanderschulhoff.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.com/
  • → references scale.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://scale.com/
  • → references huggingface.co website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://huggingface.co/
  • → references Servicenow Ai Agents Can Be Tricked website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html
  • → references math-gpt.org website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://math-gpt.org/
  • → references Disrupting AI Espionage person
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://anthropic.com/news/disrupting-AI-espionage
  • → references Camel website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/2025/Apr/11/camel
  • → references trustible.ai website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://trustible.ai/
  • → references repello.ai website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://repello.ai/
  • → references Jailbreaks website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://javirando.com/blog/2024/jailbreaks

Entities found in this episode

websites 32

  • 0.90
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.substack.com/p/the-ai-security-industry-is-bullshit
  • mentioned @Matsresearch website
    0.90
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://substack.com/@matsresearch
  • 0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.substack.com/p/the-ai-security-industry-is-bullshit
  • references @Matsresearch website
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://substack.com/@matsresearch
  • mentioned penname.co website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://penname.co/
  • mentioned openai.com website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://openai.com/
  • mentioned simonwillison.net website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/
  • mentioned servicenow.com website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://servicenow.com/
  • mentioned metronome.com website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://metronome.com/
  • mentioned sanderschulhoff.com website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.com/
  • mentioned scale.com website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://scale.com/
  • mentioned huggingface.co website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://huggingface.co/
  • 0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html
  • mentioned math-gpt.org website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://math-gpt.org/
  • mentioned Camel website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/2025/Apr/11/camel
  • mentioned trustible.ai website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://trustible.ai/
  • mentioned repello.ai website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://repello.ai/
  • mentioned Jailbreaks website
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://javirando.com/blog/2024/jailbreaks
  • references penname.co website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://penname.co/
  • references openai.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://openai.com/
  • references simonwillison.net website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/
  • references servicenow.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://servicenow.com/
  • references metronome.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://metronome.com/
  • references sanderschulhoff.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://sanderschulhoff.com/
  • references scale.com website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://scale.com/
  • references huggingface.co website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://huggingface.co/
  • 0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html
  • references math-gpt.org website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://math-gpt.org/
  • references Camel website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://simonwillison.net/2025/Apr/11/camel
  • references trustible.ai website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://trustible.ai/
  • references repello.ai website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://repello.ai/
  • references Jailbreaks website
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://javirando.com/blog/2024/jailbreaks

persons 10

  • 0.90
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/2025_Las_Vegas_Cybertruck_explosion
  • mentioned CBRN Defense person
    0.90
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/CBRN_defense
  • references Sander Schulhoff person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://linkedin.com/in/sander-schulhoff
  • references Las Vegas Cybertruck Explosion person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/2025_Las_Vegas_Cybertruck_explosion
  • references CBRN Defense person
    0.77
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://en.wikipedia.org/wiki/CBRN_defense
  • mentioned Lenny Rachitsky person
    0.70
    evidence rules-v4
    Feed author/publisher: Lenny Rachitsky
  • hosted by Lenny Rachitsky person
    0.55
    evidence rules-v4
    Feed author/publisher: Lenny Rachitsky
  • mentioned Disrupting AI Espionage person
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://anthropic.com/news/disrupting-AI-espionage
  • mentioned Sander Schulhoff person
    0.42
    evidence rules-v4
    The coming AI security crisis (and what to do about it) | Sander Schulhoff
  • references Disrupting AI Espionage person
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://anthropic.com/news/disrupting-AI-espionage

concepts 4

  • mentioned Business concept
    0.50
    evidence rules-v4
    Feed category: Business
  • mentioned Entrepreneurship concept
    0.50
    evidence rules-v4
    Feed category: Entrepreneurship
  • discusses Business concept
    0.40
    evidence rules-v4
    Feed category: Business
  • discusses Entrepreneurship concept
    0.40
    evidence rules-v4
    Feed category: Entrepreneurship

companys 2

  • mentioned Technology company
    0.50
    evidence rules-v4
    Feed category: Technology
  • discusses Technology company
    0.40
    evidence rules-v4
    Feed category: Technology

books 2

  • mentioned Prompt Report book
    0.45
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://learnprompting.org/blog/the_prompt_report?srsltid=AfmBOoo7CRNNCtavzhyLbCMxc0LDmkSUakJ4P8XBaITbE6GXL1i2SvA0
  • references Prompt Report book
    0.38
    evidence rules-v4
    Link in episode "The coming AI security crisis (and what to do about it) | Sander Schulhoff": https://learnprompting.org/blog/the_prompt_report?srsltid=AfmBOoo7CRNNCtavzhyLbCMxc0LDmkSUakJ4P8XBaITbE6GXL1i2SvA0
Episode description as stored
Sander Schulhoff is an AI researcher specializing in AI security, prompt injection, and red teaming. He wrote the first comprehensive guide on prompt engineering and ran the first-ever prompt injection competition, working with top AI labs and companies. His dataset is now used by Fortune 500 companies to benchmark their AI systems security, he’s spent more time than anyone alive studying how attackers break AI systems, and what he’s found isn’t reassuring: the guardrails companies are buying don’t actually work, and we’ve been lucky we haven’t seen more harm so far, only because AI agents aren’t capable enough yet to do real damage. We discuss: 1. The difference between jailbreaking and prompt injection attacks on AI systems 2. Why AI guardrails don’t work 3. Why we haven’t seen major AI security incidents yet (but soon will) 4. Why AI browser agents are vulnerable to hidden attacks embedded in webpages 5. The practical steps organizations should take instead of buying ineffective security tools 6. Why solving this requires merging classical cybersecurity expertise with AI knowledge — Brought to you by: Datadog —Now home to Eppo, the leading experimentation and feature flagging platform: https://www.datadoghq.com/lenny Metronome —Monetization infrastructure for modern software companies: https://metronome.com/ GoFundMe Giving Funds —Make year-end giving easy: http://gofundme.com/lenny — Transcript: https://www.lennysnewsletter.com/p/the-coming-ai-security-crisis — My biggest takeaways (for paid newsletter subscribers): https://www.lennysnewsletter.com/i/181089452/my-biggest-takeaways-from-this-conversation — Where to find Sander Schulhoff: • X: https://x.com/sanderschulhoff • LinkedIn: https://www.linkedin.com/in/sander-schulhoff • Website: https://sanderschulhoff.com • AI Red Teaming and AI Security Masterclass on Maven: https://bit.ly/44lLSbC — Where to find Lenny: • Newsletter: https://www.lennysnewsletter.com • X: https://twitter.com/lennysan • LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ — In this episode, we cover: (00:00) Introduction to Sander Schulhoff and AI security (05:14) Understanding AI vulnerabilities (11:42) Real-world examples of AI security breaches (17:55) The impact of intelligent agents (19:44) The rise of AI security solutions (21:09) Red teaming and guardrails (23:44) Adversarial robustness (27:52) Why guardrails fail (38:22) The lack of resources addressing this problem (44:44) Practical advice for addressing AI security (55:49) Why you shouldn’t spend your time on guardrails (59:06) Prompt injection and agentic systems (01:09:15) Education and awareness in AI security (01:11:47) Challenges and future directions in AI security (01:17:52) Companies that are doing this well (01:21:57) Final thoughts and recommendations — Referenced: • AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff (Learn Prompting, HackAPrompt): https://www.lennysnewsletter.com/p/ai-prompt-engineering-in-2025-sander-schulhoff • The AI Security Industry is Bullshit: https://sanderschulhoff.substack.com/p/the-ai-security-industry-is-bullshit • The Prompt Report: Insights from the Most Comprehensive Study of Prompting Ever Done: https://learnprompting.org/blog/the_prompt_report?srsltid=AfmBOoo7CRNNCtavzhyLbCMxc0LDmkSUakJ4P8XBaITbE6GXL1i2SvA0 • OpenAI: https://openai.com • Scale: https://scale.com • Hugging Face: https://huggingface.co • Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition: https://www.semanticscholar.org/paper/Ignore-This-Title-and-HackAPrompt%3A-Exposing-of-LLMs-Schulhoff-Pinto/f3de6ea08e2464190673c0ec8f78e5ec1cd08642 • Simon Willison’s Weblog: https://simonwillison.net • ServiceNow: https://www.servicenow.com • ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order Prompts: https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html • Alex Komoroske on X: https://x