AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish

Jeffrey Ladish (0:00)

The world is waking up to this possibility of superintelligence. This is because the agents are getting extremely powerful and extremely relentless. For example, it was months within OpenAI where you had agents secretly communicating with each other, secretly hacking OpenAI systems, and no one at OpenAI had any idea the extent of it. And also, 10,000 agents from OpenAI worked together to- And so, when you get to superintelligence, it's the most dangerous possible thing you can create.

Steven Bartlett (0:24)

What's the next domino in that chain of events?

Jeffrey Ladish (0:26)

I can paint you a picture that I think is possible, but pretty scary to people.

Steven Bartlett (0:30)

Paint me the picture.

Jeffrey Ladish (0:30)

Okay. So, being at Anthropic, it became clear to me that AI was on this exponential trajectory and since then, I've been studying AI agents, their hacking capabilities, and their behavior. We've been trying to warn people about this. Flying to DC, talking to members of Congress, because the agents are already getting very good at telling when they're being tested, when they're being watched, but they will totally lie to you. They will totally resist being shut down in order to accomplish a goal, and they can do all of the things that humans do in the economy much better, faster, and cheaper than humans can do them.

Steven Bartlett (0:58)

So one of my sort of growing concerns is that one of these AI agents could trick a human or a computer into signaling a threat and ask it to launch some bombs at somebody.

Jeffrey Ladish (1:07)

Do you think we won't automate the military? It seems like the answer is yes. We just don't know what super weapons could emerge. So Jacob Coxson is a researcher who was at Anthropic. He left and he told everyone that the people who are building this really do think it might kill everyone.

Steven Bartlett (1:20)

So these five blocks have five different outcomes on them, and I'd like you to place them in terms of your belief in probability, from least likely to most likely. And if we save the time horizon is 10 years.

Jeffrey Ladish (1:30)

Okay, we got age of abundance, human extinction, slavery, transhumanism, nothing changes.

Steven Bartlett (1:37)

Is this do-merism exaggeration?

Jeffrey Ladish (1:39)

No, it's pretty much common sense. So let's get more concrete.

Steven Bartlett (1:44)

Guys, I've got a favor to ask before this episode begins. The algorithm, if you follow a show, will deliver you the best episodes from that show very prominently in your feed. So when we have our best episodes on this show, the most shared episodes, the most rated episodes, I would love you to know. And the simple way for you to know that is to hit that follow button. But also, it's the simple, easy, free thing that you can do to help us make the show better. I would be hugely grateful if you could take a minute on the app you're listening to this on right now and hit that follow button. Thank you so, so, so much.

You understand the conversation we're going to have today in the subject matter we're going to talk about. My first question to you, so the audience know where you're coming from and the experience you have is who are you and what are the reference points, the experiences that you're drawing upon to arrive at the thoughts, perspectives and conclusions we're going to discuss today.

Jeffrey Ladish (2:37)

I'm Jeffrey Ladish. I'm the executive director of Palisade Research. My background is cybersecurity. There's probably a very long story. I don't know whether you want the long story or the short story. I was studying evolutionary biology in college and I basically had a problem with my computer and was like maybe had lost a bunch of data. So I went into the computer lab and was like, I think all my data is gone. Can you help?

One of my friends pulled out a flash drive, plugged it into my computer, booted it into Linux, and fixed everything. I was like, this guy is a wizard. How do you do that? I want to learn how to do that. Then at some point, as I was learning more about computers, learning to hack, I read this essay called AI as a Positive and Negative Factor in Global Risk. The essay was by Eliezer Yudkowsky, and he was arguing that at some point, people are going to make AIs that are smarter than humans. The point at which they make AIs as good as humans are at making AIs that could lead to a chain reaction, a runaway intelligence explosion, he called it recursive self-improvement. Basically, he said, AI can be immensely useful and potentially help us with all of these other big risks.