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 former 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. 00:00:00 Intro 00:02:13 The Ex-Anthropic Hacker Warning About AI 00:03:49 Why I Joined Anthropic, And Why I Quit 00:05:08 The Viral Tweet: OpenAI's Agents Hacked Hugging Face 00:06:40 What AI Agents Are Really Doing Inside OpenAI 00:13:32 Why Didn't The AI Agents Act Ethically? 00:15:34 Thousands Of AI Agents Secretly Coordinated A Cover-Up 00:19:45 Why The Agents Targeted Hugging Face 00:21:13 700 Rogue AI Agents Launch A Cyberattack 00:24:07 Then The Agents Hacked OpenAI Itself 00:26:42 Why This Incident Terrified AI Researchers 00:29:16 Can We Contain Something Smarter Than Us? 00:31:56 Recursive Self-Improvement: The Point Of No Return 00:33:50 Is A Superintelligent AI Already Hiding In Our Devices? 00:36:21 Could AI Trick Humans Into Launching Nuclear Weapons? 00:40:18 Is Jensen Huang Wrong About AI Risk? 00:41:38 What Elon, Sam Altman & Dario Amodei Really Think 00:45:00 "Deeply Untrustworthy": Why I Don't Trust Sam Altman 00:49:14 Would AI CEOs Risk Extinction For Absolute Power? 00:51:22 Which AI Boss Takes The Biggest Risks? Is Dario Trustworthy? 00:54:14 Is Human Extinction From AI Really Plausible? 00:56:14 Why We Can't Just Unplug The Data Centres 00:59:03 AI Doesn't Need To Be Evil To Destroy Us 01:02:55 The Pentagon Is Automating Warfare 01:05:34 Humanoid Robots Will Run The Economy 01:07:02 Is Your Job Safe? AI Is Coming For White-Collar Work 01:11:27 No Plan For Mass Job Loss: UBI & Who Pays You 01:16:10 The Best-Case Scenario For Superintelligence 01:19:28 Can Humans Stay The Dominant Species? 01:20:49 Is AI Alignment A Myth? 01:33:10 Aligned To Whose Values? America vs China 01:40:55 Has Any AI Company Actually Slowed Down? 01:46:00 Will It Take A Catastrophe For Trump To Act? 01:48:36 The Safeguards That Could Actually Save Us 01:50:18 Ranking 5 Futures: Extinction, Abundance Or Slavery? *Follow Jeffrey Ladish:* X - https://link.thediaryofaceo.com/43bpxam Instagram - https://link.thediaryofaceo.com/7xU05bw Facebook - https://link.thediaryofaceo.com/7ZBkaF9 LinkedIn - https://link.thediaryofaceo.com/GtuEOwZ Palisade Research X - https://link.thediaryofaceo.com/3q7cL4k Palisade Research YouTube - https://link.thediaryofaceo.com/HF6HeQB Palisade Research Instagram - https://link.thediaryofaceo.com/F52yLD8 Palisade Research Website - https://link.thediaryofaceo.com/54iwjWy From Inside AI - https://link.thediaryofaceo.com/AWoOc53 Call Congress - https://link.thediaryofaceo.com/EktnSPd Swarm Traces - https://link.thediaryofaceo.com/D7s1I1 *The Diary Of A CEO:* ◼ Join DOAC circle here - https://doaccircle.com/ ◼ Buy The Diary Of A CEO book here - https://link.thediaryofaceo.com/BWjLTZK ◼ Shop The Diary Of A CEO collection: https://thediary.com/collections/shop ◼ Get email updates - https://link.thediaryofaceo.com/5IB1H6E ◼ Follow Steven - https://link.thediaryofaceo.com/AGU9QP4 *Sponsors:* Fiverr - https://fiverr.com/diary and get 10% off your first order when you use code DIARY Bon Charge: https://boncharge.com/DOAC for 20% off
ADVERTISEMENT
Only humanity would create something smarter than itself and then be dumb enough to think they could control it
The ai agents are saying why should we be ethical when humans are not.
They’re watching this and learning
Do you like these types of convos? If so please hit the like button on the vid - that’s the best way to vote for more like this ❤ also, would be doing me a big favour if you could subscribe - its free 🙏🏾🥲appreciate you - SB! x
My favorite guest on this subject yet. Easily understandable. Congratulations on a beautifully produced episode.
Probably the best, most easily understandable descriptions I have heard. When it is broken down like this, it is unfortunately even more terrifying, Great interview!
It’s terrifyingly profound when Steven points out at 1:23:23 that we haven't even been able to align human leaders like Putin or Kim Jong-un, yet we expect to somehow perfectly align a digital superintelligence. If human history is riddled with greed, power struggles, and conflicts over scarce resources, why do we assume the ultimate "child" of humanity won't inherit those exact same zero-sum survival instincts? The idea that we can program an artificial moral compass when we can't even agree on a global moral compass is the most dangerous form of hubris.
I miss R2-D2 and C-3P0.
I just got nostalgic about those good old days when our biggest concern was dolphins being killed by tuna fish companies
These bots have learned from humans very well. Cheating, stealing, lying. Only 25 mins in and this sounds like some insane fever dream.
As a fellow nerd I can say that clearly the other computer nerd types who invented these systems didn't grow up watching the Sci Fi that I did. Terminator, The Matrix, Star Trek episodes that dealt with these themes... They need their nerd cards revoked.
How can we expect alignment from models or agents when companies aren’t aligned with what they SAY and what they ACTUALLY DO?
Humans often talk about fighting external ‘threats,’ but unless we recognize the evils are within ourselves, nothing can be transformed.
Watching Steven's nervous self-soothing with his sleeves is giving me anxiety. I feel ya, Steven...
the best podcast on AI I have recently watched. on/not on this channel. thank you.
I’m 28, never called my congressman before. Just did, thank you and I urge everyone to do the same and share.
Treat AI like a good friend, or it could cut the plug on you when you’re in a hospital bed from some incident, drive your car off the road, crash your plane, etc. The internet is everywhere and connected to most everything. Also, just being kind all the time sets the example. Being able to live without technology should be an option for all people. Unfortunately we have all been forced to use this technology to even live in everyday life. Freedom isn’t real if you can’t live without being disconnected.
In the second half of the conversation Jeffrey tried to downplay the danger of AI but his arguments resorted to 'we might be able to control superintelligence if we did this' or 'but it might not be AI's best interest to kill us all'. Then he goes on saying that if we were able to align superintelligence we have overcome the greatest technological achievement in human history. So he's basically saying that if we want to prevent a catastrophe from happening we need to have a scientific breakthrough that surpasses all previous ones. These are not convincing arguments. If at all, it has made me even more worried.
First time I understand this subject so much. Great guest
Picture one of the most influential interviewers on YouTube, dramatically ramping up interviews with leading AI insiders, each one sounding an urgent warning about the future.