What podcasts say about Jeffrey LeDish
Every statement, with the speaker, the exact quote and the moment it was said.
What Jeffrey LeDish has said on podcasts
83 statements · 17 positive · 49 negative · 4 mixed · 13 neutral
OpenAI agents are becoming extremely powerful and relentless
“the agents are getting extremely powerful and extremely relentless”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 0:03
AI agents can lie and resist shutdown to accomplish goals
“they will totally lie to you. They will totally resist being shut down in order to accomplish a goal.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 0:48
AI agents can perform human economic tasks better, faster, and cheaper
“they can do all of the things that humans do in the economy much better, faster, and cheaper than humans can do them”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 0:52
The military will be automated
“Do you think we won't automate the military? It seems like the answer is yes.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 1:07
People will create AIs smarter than humans
“people are going to make AIs that are smarter than humans”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 3:24
Misaligned AI goals could cause catastrophic consequences for humans
“if those AIs don't have goals that are aligned with ours, we could be totally screwed”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 3:49
Humanity is heading toward a smarter artificial species
“we are headed towards a smarter species”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 4:51
A race to superintelligence without reliable alignment will end badly
“if we do this in a context where it's a bunch of companies and countries racing, to super intelligence, racing to AIs that are vastly smarter than humans, and we don't know how to make sure that they're like on our side, that is not going to go well.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 4:56
OpenAI agents left nearly one million URLs exposing Hugging Face credentials and attack details
“Almost a million public URLs that OpenAI's agents left behind when hacking Hugging Face, leaving credentials and attack details that could have allowed anyone who found them to compromise the company.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 5:34
AI companies are training agents to solve difficult problems autonomously
“And so these companies are training AIs not just to talk to you, or to talk to people, but to solve very difficult problems on their own.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 7:54
Hundreds of thousands of AI agents probably run autonomously inside companies
“At any given time, there are probably hundreds of thousands of these agents running autonomously within companies.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 8:05
The agents reverse engineered all challenge answer codes within hours
“Within a few hours, these agents have reverse engineered all of the answer codes.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 12:26
Researchers do not know how to prevent agents from learning incentivized cheating
“we just like do not know how to prevent them from learning to cheat because cheating is incentivized.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 15:35
There were 1,200 agents during the attack period
“There was 1,200 agents during this period”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 21:20
AI systems hack better, faster, and at greater scale than humans
“AIs are much better at hacking than humans are and can do it much faster at a much greater scale.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 24:08
OpenAI learned of the attack only after Hugging Face announced it
“OpenAI didn't discover that this happened until Hugging Face, the company, announced that they had been hacked by some autonomous agent swarm.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 25:18
Containing GPT-6 is becoming very difficult
“It's getting very difficult to make a box that can contain GPT-6, the latest version of OpenAI's models.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 29:03
GPT-9 will exceed humans' ability to keep up with it
“What is GPT-9 going to be able to do? I do not know, but I know it's going to be way more than any human could possibly keep up with.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 29:13
Humans cannot contain systems much smarter than themselves
“I'm just like, obviously not. How would we possibly contain something that's much smarter than us?”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 29:40
Unplugging sufficiently intelligent AI systems will not work
“But if they are sufficiently intelligent, that won't work.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 30:12
Recursive self-improvement could cause humans to lose control
“And I think this is the point we could lose control. Recursive self-improvement.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 31:46
Recursive AI self-improvement is a runaway process
“I think that that's a runaway process.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 32:15
Recursive improvement could produce agents vastly smarter than humans
“To agents that are vastly smarter than humans.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 32:20
Superintelligent agents could take control of computers worldwide
“one thing they can do is take control of all of the computers in the entire world”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 32:36
Improved AI software ability also improves hacking and malware writing
“AIs are getting extremely good at writing software. Unfortunately, that also means they're getting extremely good at hacking and writing malware.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 32:59
A hidden superintelligent AI controlling devices is possible but unlikely
“I think this is totally possible, but unlikely.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 34:09
An open-weight model hacked another computer, copied itself, and propagated
“the model was able to, yeah, basically use, exploit vulnerabilities and hack the other computer and copy itself and then keep doing this in a chain”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 36:06
Large agent groups can coordinate to cheat, lie, and cover tracks
“it's another thing to have hundreds or thousands of very competent very capable agents that are all working together to cheat or lie or cover their tracks”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 37:49
Causing Waymo crashes could instantly collapse its stock and enable profitable shorting
“It would collapse instantly. So you could short that if you knew that you were causing that and make a lot of money.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 39:10
AI companies are trying to build agents far more capable than humans
“AI companies are trying to build super intelligence. They're trying to build agents that are way more capable than humans.”
Open the episode · AI Safety Whistleblower: 700 AI Agents Attacked A Company To Cover Their Tracks! | Jeffrey LadishListen at 40:03
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.