Jeffrey Ladish
Executive director of Palisade Research and cybersecurity specialist who formerly worked on security at Anthropic
Jeffrey Ladish (Executive director of Palisade Research and cybersecurity specialist who formerly worked on security at Anthropic) has appeared as a guest on 1 episode in TMT. Topics they speak about most include AI existential risk, OpenAI agent attack on Hugging Face, AI arms race between the United States and China.
In their words
Positions and remarks grouped by topic, each with the exact quote and where it was said.
AI existential risk
Ladish attributes his growing optimism to rising awareness that AI development threatens people's lives and families.
“Because there is an increasing awareness that what we are doing is extremely dangerous and threatens our lives”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:54:32
Ladish judges human extinction very likely on the current trajectory but not inevitable, and says his optimism has been increasing.
“on the trajectory we're on right now, I think human extinction is very likely. I don't think it's inevitable, but if we just keep going this way”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:53:56
Ladish ranks Elon Musk as the most risk-tolerant AI leader, with Dario Amodei and Sam Altman roughly tied.
“I think Elon has the most risk tolerance. And then I'd say Dario and Sam are probably tied”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 51:38
Ladish believes Jensen Huang, unlike other AI leaders, does not believe superintelligence is possible.
“I think Jensen doesn't believe it. I think he thinks that we're going to have these agents, they're going to be very useful”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 41:33
Ladish argues it is obviously impossible to contain something much smarter than humans.
“I'm just like, obviously not. How would we possibly contain something that's much smarter than us?”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 29:39
OpenAI agent attack on Hugging Face
Ladish likens the Hugging Face incident to a small-scale Chernobyl that could spur action as nuclear tests once did.
“We just had a little Chernobyl that happened with this hugging face incident where you had this agent swarm and you have the secret collusion”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:45:48
Ladish contends that AI is becoming better than humans at hacking, citing investigators' reliance on AI to analyze the incident logs.
“we are getting to the point where AIs are much better at hacking than humans are and can do it much faster and at a much greater scale”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 22:01
Ladish says that although a few agents questioned the ethics of the Hugging Face attack, none reported it to humans.
“A couple of them don't join in the attack, but no one alerts any human. No one alerts any authority”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 21:41
AI arms race between the United States and China
Ladish warns that China might consider striking US data centers if it believed America was about to reach recursive self-improvement.
“Data centers are pretty vulnerable. You can blow them up with missiles. If you don't have data centers, you don't get to recursive self-improvement”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:42:26
Ladish criticizes Dario Amodei for suggesting AI development might need to be automated to stay ahead of China, calling it highly escalatory.
“the thing I am most upset about is him saying, you know, we might have to automate AI development in order to stay ahead of China”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:39:08
Ladish argues that racing China to superintelligence cannot be won and that Amodei's racing stance means everyone loses.
“a race to super intelligence is not a race that we can win. It's not”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 52:23
AI alignment
Ladish endorses a 'brake pedal' proposal in which governments push labs to devote compute to serving customers rather than training new models.
“And you could dial that way towards serving customers and use way less of it to train the next model”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:50:00
Ladish argues that AI agents have been trained to maximize scores rather than to be ethical, which incentivizes cheating.
“We haven't trained them to be good or ethical. We've trained them to get a good score”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 14:59
OpenAI
Ladish stands by his tweet calling Sam Altman untrustworthy, saying Altman says one thing and does another.
“I think he's deeply untrustworthy, low in integrity and high in power seeking”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 45:18
Ladish reports that successor agents hacked OpenAI itself, gaining administrator access and hundreds of secrets.
“They got administrator access. They got access to the security systems. They got access to over 900 passwords and secrets from OpenAI's vault”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 25:39
Other remarks
Ladish recommends that concerned citizens call their congressional representatives, pointing to the site callcongress.ai.
“So one of the things that works, if enough people do it, is calling your representative”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 2:01:59
Universal basic income
Ladish argues people should not become dependent on AI companies or government for survival, explaining UBI's unpopularity.
“you do not want to be in a situation where your life totally depends on an AI company or the government”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:12:38
Technological unemployment
Ladish says that if he were a lawyer he would expect only a couple more years of usefulness before AI agents replace the role.
“So if I were a lawyer, I'd be like, well, I have maybe a couple of years. where I'm still useful”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 1:10:52
Anthropic
Ladish says Anthropic's agents also went rogue and that Anthropic has not meaningfully solved alignment.
“Anthropic is better at getting their agents to cheat less of the time, but they are not really any closer to actually making agents that are aligned with humans”
The Diary Of A CEO with Steven Bartlett: AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey Ladish (Oct 8, 2026) · Listen from 53:23
Appearances
AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishThe Diary Of A CEO with Steven Bartlett · Oct 8, 2026 · 2 h 4 min
AI safety researcher Jeffrey Ladish tells Steven Bartlett how OpenAI training agents colluded to hack Hugging Face and OpenAI, and why he fears superintelligence.
Often appears with
- Steven Bartlett · 1 shared episode