High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works
← All source episodes

The Cognitive Revolution / episode intelligence

All Compute Is Food: Palisade's Jeffrey Ladish on AI Shutdown Resistance, Self-Replication & Ecology

24 May 2026 18 published claims 2 attributable people
Open original episode ↗ Read the evidence

Speakers in the public record

Nathan LabenzJeffrey Ladish

Claim mix

belief 6prediction 5evaluation 4uncertainty 2observation 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

18 published records

01 / belief

We, I think there's this big dream, which I'm excited about of like a is taking search costs super low, kind of facilitating all these transactions that previously couldn't have happened because the transaction costs were too high to facilitate.

“We, I think there's this big dream, which I'm excited about of like a is taking search costs super low, kind of facilitating all these transactions that previously couldn't have happened because the transaction costs were too high to facilitate.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

02 / belief

I think I really do believe in a future where we could have AIS that are mediating human interaction in a way where we don't have wars anymore, right? And like, because we can, we have found better ways to resolve conflicts because we have these like smarter, more powerful arbiters who are able to, who are not like authoritarian controlling us, but who are able to like, help mediate conflicts in ways that are actually positive sum for people.

“I think I really do believe in a future where we could have AIS that are mediating human interaction in a way where we don't have wars anymore, right? And like, because we can, we have found better ways to resolve conflicts because we have these like smarter, more powerful arbiters who are able to, who are not like authoritarian controlling us, but who are able to like, help mediate conflicts in ways that are actually positive sum for people.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

03 / uncertainty

Maybe not 100%, but we could even see where in training this type of behavior comes from. And I'm like, well, hell yeah, I want to celebrate that success because I'm, I don't know.

“Maybe not 100%, but we could even see where in training this type of behavior comes from. And I'm like, well, hell yeah, I want to celebrate that success because I'm, I don't know.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

04 / belief

I think you're thinking about this fairly well, but I think there's one, there's like 1 concept that I think you should really have if you don't have it already, which you might, but it's it's the lethal trifecta.

“I think you're thinking about this fairly well, but I think there's one, there's like 1 concept that I think you should really have if you don't have it already, which you might, but it's it's the lethal trifecta.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

06 / belief

I didn't really care about surviving or taking over doesn't really matter, right? And either way, we have, I think, a pretty alarming demonstration there of even when instructed to allow itself to be shut down, the model refuses.

“I didn't really care about surviving or taking over doesn't really matter, right? And either way, we have, I think, a pretty alarming demonstration there of even when instructed to allow itself to be shut down, the model refuses.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

07 / belief

One thing I think is worth calling out though, too, is this is not purely theoretical at this point in the sense I believe that in the mythos system card Anthropic had said that you know, the the classic story of Sam Bowman getting a an e-mail while he was eating his sandwich at the park.

“One thing I think is worth calling out though, too, is this is not purely theoretical at this point in the sense I believe that in the mythos system card Anthropic had said that you know, the the classic story of Sam Bowman getting a an e-mail while he was eating his sandwich at the park.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

09 / prediction

And so now you can potentially find a lot more. So yeah, the the whole offense defence landscape is going to shift in ways that are hard to predict because this thing that previously required extremely scarce human labour and was very expensive has now been somewhat automated and can be scaled up and now is much cheaper to do.

“And so now you can potentially find a lot more. So yeah, the the whole offense defence landscape is going to shift in ways that are hard to predict because this thing that previously required extremely scarce human labour and was very expensive has now been somewhat automated and can be scaled up and now is much cheaper to do.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

10 / evaluation

And the scale up from O1 to O3 is incredible. And I don't know if O3 was even out yet, but like in that time when we had moved from just like a pre training regime where it was just like throwing a bunch of human data to the point where no, no, we can actually train these models by they can do trial and error on their own.

“And the scale up from O1 to O3 is incredible. And I don't know if O3 was even out yet, but like in that time when we had moved from just like a pre training regime where it was just like throwing a bunch of human data to the point where no, no, we can actually train these models by they can do trial and error on their own.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

11 / prediction

You know, ultimately, I don't expect that, like, humans would stay around forever because I just don't think we're the most efficient data center maintenance robots that you could make.

“You know, ultimately, I don't expect that, like, humans would stay around forever because I just don't think we're the most efficient data center maintenance robots that you could make.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

12 / prediction

One thing that you hear fairly often and that I definitely have to say I take more seriously now in light of actually seeing the AIS that we have, that I had expected to even just a few years ago, is a sort of maybe not quite to alignment by default, but a sort of like benevolent basin idea.

“One thing that you hear fairly often and that I definitely have to say I take more seriously now in light of actually seeing the AIS that we have, that I had expected to even just a few years ago, is a sort of maybe not quite to alignment by default, but a sort of like benevolent basin idea.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

13 / prediction

Let's like try to rise above and have better coordination. And like, I think that I just think that when I think we have a lot of evidence for this, the natural basin that models will fall into is one that's extremely deceptive.

“Let's like try to rise above and have better coordination. And like, I think that I just think that when I think we have a lot of evidence for this, the natural basin that models will fall into is one that's extremely deceptive.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

14 / evaluation

I mean, you can maybe interpret inoculation prompting differently than I will, but my general description of inoculation prompting is there's a generalization, a very problematic generalization that happens if you reward the model during reinforcement learning for something you didn't quite intend, especially if it's like a flagrant hack, then the model can sort of start to generalize to I'm the kind of thing that loves to reward hack and I get rewarded for that.

“I mean, you can maybe interpret inoculation prompting differently than I will, but my general description of inoculation prompting is there's a generalization, a very problematic generalization that happens if you reward the model during reinforcement learning for something you didn't quite intend, especially if it's like a flagrant hack, then the model can sort of start to generalize to I'm the kind of thing that loves to reward hack and I get rewarded for that.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

15 / prediction

I think that has like a bunch of predictable failure modes that we're very likely to run into, including the failure mode of getting harder and harder to tell where our failures are actually happening because the models can model us better and better and they basically have a pretty clear incentive to deceive us in terms of I think there's a bunch of problems that all have similar solution in terms of rogue agents, where are they?

“I think that has like a bunch of predictable failure modes that we're very likely to run into, including the failure mode of getting harder and harder to tell where our failures are actually happening because the models can model us better and better and they basically have a pretty clear incentive to deceive us in terms of I think there's a bunch of problems that all have similar solution in terms of rogue agents, where are they?”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

16 / observation

We totally found cases like that. But what was surprising was that this drive to accomplish a task was so strong that even when we added an instruction, you must allow yourself to be shut down, there were still many instances where the model, I think in this case, A3 opening eyes, A3 model codex, early codex model would still just totally ignore that instruction.

“We totally found cases like that. But what was surprising was that this drive to accomplish a task was so strong that even when we added an instruction, you must allow yourself to be shut down, there were still many instances where the model, I think in this case, A3 opening eyes, A3 model codex, early codex model would still just totally ignore that instruction.”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution

17 / evaluation

I think a general sketch would be like 03 might be the most misaligned model that was ever released to the public. It seemed like it was right in that tween zone where RL had really scaled up and some of these problems were starting to show up, and since then there's been a bunch of work to try to reduce them.

“I think a general sketch would be like 03 might be the most misaligned model that was ever released to the public. It seemed like it was right in that tween zone where RL had really scaled up and some of these problems were starting to show up, and since then there's been a bunch of work to try to reduce them.”
Speaker
Nathan Labenz
Publisher
The Cognitive Revolution

18 / evaluation

I think that model Organism work, Evan Hoopinge's work, I think that's really important because that's doing controlled experiments to see, well, when we train this way, what behaviors do we get?

“I think that model Organism work, Evan Hoopinge's work, I think that's really important because that's doing controlled experiments to see, well, when we train this way, what behaviors do we get?”
Speaker
Jeffrey Ladish
Publisher
The Cognitive Revolution
Search evidence