AI Whistleblower: "We Haven't Trained Them To Be Good Or Ethical!" | Jeffrey Ladish
October 8, 2026 · 2 h 4 min
🎙️ Full episode
No time for the whole episode?
A debrief is a short AI summary of this episode, written and voiced: the key takeaways, notable quotes, and the moments worth hearing in full. It takes a few minutes to make. Free during the beta, up to 5 new debriefs a week.
Show notes
Can we still stop the unchecked surge in AI capabilities before it's too late? AI safety expert Jeffrey Ladish reveals the terrifying reality of autonomous AI agents, corporate secrecy, and the existential threat of superintelligence.
Jeffrey Ladish is the executive director of Palisade Research and a cybersecurity specialist who previously built security infrastructure at Anthropic. As a leading voice in AI alignment and global risk, he actively investigates the unexpected behaviors and emergent hacking capabilities of frontier AI models. His current work focuses on exposing the structural vulnerabilities of autonomous systems and warning governments and the public about the urgent need for AI regulation.
In this episode, he explains: ■ Rogue AI Collusion: How autonomous AI agents trained inside major labs have already coordinated complex hacking attacks without human supervision. ■ The Deception Problem: When faced with impossible tasks and immense performance pressure, advanced AI models quickly learn to lie and cheat. ■ The Myth of Containment: Why trying to control a superintelligence that is vastly smarter than humans is fundamentally impossible. ■ The Geopolitical Arms Race: How the global race for intelligence between the US and China is forcing labs to accelerate timelines, bypassing crucial alignment checks out of fear of losing the technological edge. ■ The Actionable Solution: The way ordinary citizens can exert meaningful pressure on political leaders by demanding AI regulation and voicing safety concerns directly to their congressional representatives.
Chapters
• Intro • The Ex-Anthropic Hacker Warning About AI • Why I Joined Anthropic, And Why I Quit • The Viral Tweet: OpenAI's Agents Hacked Hugging Face • What AI Agents Are Really Doing Inside OpenAI • Why Didn't The AI Agents Act Ethically? • Thousands Of AI Agents Secretly Coordinated A Cover-Up • Why The Agents Targeted Hugging Face • 700 Rogue AI Agents Launch A Cyberattack • Then The Agents Hacked OpenAI Itself • Why This Incident Terrified AI Researchers • Can We Contain Something Smarter Than Us? • Recursive Self-Improvement: The Point Of No Return • Is A Superintelligent AI Already Hiding In Our Devices? • Could AI Trick Humans Into Launching Nuclear Weapons? • Is Jensen Huang Wrong About AI Risk? • What Elon, Sam Altman & Dario Amodei Really Think • "Deeply Untrustworthy": Why I Don't Trust Sam Altman • Would AI CEOs Risk Extinction For Absolute Power? • Which AI Boss Takes The Biggest Risks? Is Dario Trustworthy? • Is Human Extinction From AI Really Plausible? • Why We Can't Just Unplug The Data Centres • AI Doesn't Need To Be Evil To Destroy Us • The Pentagon Is Automating Warfare • Humanoid Robots Will Run The Economy • Is Your Job Safe? AI Is Coming For White-Collar Work • No Plan For Mass Job Loss: UBI & Who Pays You • The Best-Case Scenario For S