High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Eliezer Yudkowsky

Published podcast speaker

Claims
44
Episodes
1
Shows
1
Named items
0

Claim ledger

What Eliezer said.

44 transcript-backed records

01 / uncertainty

I guess because I could be wrong and because matters are now serious enough that I have nothing left to do but go out there and tell people how it looks and maybe someone thinks of something I did not think of.

“I guess because I could be wrong and because matters are now serious enough that I have nothing left to do but go out there and tell people how it looks and maybe someone thinks of something I did not think of.”
Publisher
Dwarkesh Podcast

03 / belief

I think that if you actually go start trying to run a project of selectively encouraging some marriages between particular people and encouraging them to have children, you will rapidly find, as one does in any such process that when you select on the stuff you want, it turns out there’s a bunch of stuff correlated with it and that you’re not changing just one thing.

“I think that if you actually go start trying to run a project of selectively encouraging some marriages between particular people and encouraging them to have children, you will rapidly find, as one does in any such process that when you select on the stuff you want, it turns out there’s a bunch of stuff correlated with it and that you’re not changing just one thing.”
Publisher
Dwarkesh Podcast

05 / prediction

I’m trying to think about whether I expect super dogs to be sufficiently in a human frame of reference in virtue of them also being mammals.

“I’m trying to think about whether I expect super dogs to be sufficiently in a human frame of reference in virtue of them also being mammals.”
Publisher
Dwarkesh Podcast

08 / uncertainty

I’m not sure it’s enough to not have Hitler, but it sure would be a start on things going differently in a timeline. But mostly, I don’t know.

“I’m not sure it’s enough to not have Hitler, but it sure would be a start on things going differently in a timeline. But mostly, I don’t know.”
Publisher
Dwarkesh Podcast

11 / prediction

The reason why I tell people — “Yeah, don’t put your hope in the future, you’re probably dead”, is that the existence of this technical array of hope, if you do just the right things, is not the same as expecting that the world reshapes itself to permit that to be done without destroying the world in the meanwhile. I expect things to continue on largely as they have.

“The reason why I tell people — “Yeah, don’t put your hope in the future, you’re probably dead”, is that the existence of this technical array of hope, if you do just the right things, is not the same as expecting that the world reshapes itself to permit that to be done without destroying the world in the meanwhile. I expect things to continue on largely as they have.”
Publisher
Dwarkesh Podcast

12 / belief

Some of my intuition here is like I know how I would do this with dogs and I think you could ask OpenAI to describe their theory of how to do it with dogs.

“Some of my intuition here is like I know how I would do this with dogs and I think you could ask OpenAI to describe their theory of how to do it with dogs.”
Publisher
Dwarkesh Podcast

15 / evaluation

If your exit plan takes a long time, then you better shut down the academic AI journals and maybe you even have the Gestapo busting in people’s houses to accuse them of being underground AI researchers and I would really rather not live there and maybe even that doesn’t work.

“If your exit plan takes a long time, then you better shut down the academic AI journals and maybe you even have the Gestapo busting in people’s houses to accuse them of being underground AI researchers and I would really rather not live there and maybe even that doesn’t work.”
Publisher
Dwarkesh Podcast

16 / belief

” The lectures aren’t really the parts I’m proud about. It’s like where you have the life or death, deathnote style battle of wits that is centering around a series of Bayesian updates and making that actually work because it’s where I’m like — “Yeah, I think I actually pulled that off.

“” The lectures aren’t really the parts I’m proud about. It’s like where you have the life or death, deathnote style battle of wits that is centering around a series of Bayesian updates and making that actually work because it’s where I’m like — “Yeah, I think I actually pulled that off.”
Publisher
Dwarkesh Podcast

17 / belief

At the core I think what you’re describing there is a sufficiently functional society and civilization that could understand that — if they did thing X, it would lead to very bad thing Y, and so they didn’t do thing X.

“At the core I think what you’re describing there is a sufficiently functional society and civilization that could understand that — if they did thing X, it would lead to very bad thing Y, and so they didn’t do thing X.”
Publisher
Dwarkesh Podcast

18 / prediction

In historical terms, if you look out the actual battle that was being fought on the block, it was me going like — “I expect there to be AI systems that do a whole bunch of different stuff.

“In historical terms, if you look out the actual battle that was being fought on the block, it was me going like — “I expect there to be AI systems that do a whole bunch of different stuff.”
Publisher
Dwarkesh Podcast

20 / belief

I agree that possibly at this point some of them are mad at me, but I have yet to turn down the leader of any major AI lab who has come to me asking for advice.

“I agree that possibly at this point some of them are mad at me, but I have yet to turn down the leader of any major AI lab who has come to me asking for advice.”
Publisher
Dwarkesh Podcast

21 / belief

I think that you can plausibly have a series of intelligence enhancing drugs and other external interventions that you perform on a human brain and make people smarter.

“I think that you can plausibly have a series of intelligence enhancing drugs and other external interventions that you perform on a human brain and make people smarter.”
Publisher
Dwarkesh Podcast

26 / belief

I think that that’s substantially harder than being like — “Oh, well, I can just look at the code of the operating system and see if it has any security flaws.

“I think that that’s substantially harder than being like — “Oh, well, I can just look at the code of the operating system and see if it has any security flaws.”
Publisher
Dwarkesh Podcast

27 / belief

I think that the Hanson-Yudkowsky foom debate was won by Gwern Branwen, but I do think that Gwern Branwen is well to the Yudkowsky side of Yudkowsky in the original foom debate.

“I think that the Hanson-Yudkowsky foom debate was won by Gwern Branwen, but I do think that Gwern Branwen is well to the Yudkowsky side of Yudkowsky in the original foom debate.”
Publisher
Dwarkesh Podcast

31 / belief

Paul Christiano and I cooperatively fought it out really hard at trying to find a place where we both had predictions about the same thing that concretely differed and what we ended up with was Paul’s 8% versus my 16% for an AI getting gold on International Mathematics Olympics problem set by, I believe, 2025.

“Paul Christiano and I cooperatively fought it out really hard at trying to find a place where we both had predictions about the same thing that concretely differed and what we ended up with was Paul’s 8% versus my 16% for an AI getting gold on International Mathematics Olympics problem set by, I believe, 2025.”
Publisher
Dwarkesh Podcast

32 / belief

I don’t think you can even upvote downvote very well on that sort of thing. I think if you upvote-downvote, it learns to exploit the human readers.

“I don’t think you can even upvote downvote very well on that sort of thing. I think if you upvote-downvote, it learns to exploit the human readers.”
Publisher
Dwarkesh Podcast

34 / belief

Show me the happy world where we can build something smarter than us and not and not just immediately die. I think we got plenty of stuff to figure out in GPT-4.

“Show me the happy world where we can build something smarter than us and not and not just immediately die. I think we got plenty of stuff to figure out in GPT-4.”
Publisher
Dwarkesh Podcast

35 / evaluation

You could ask GPT-4 to generate 10,000 approaches to alignment and that does not get you very far because GPT-4 is not going to have very good suggestions. It’s good that we have a bunch of different people coming up with different ideas because maybe one of them works, but you don’t get a bunch of conditionally independent chances on each one.

“You could ask GPT-4 to generate 10,000 approaches to alignment and that does not get you very far because GPT-4 is not going to have very good suggestions. It’s good that we have a bunch of different people coming up with different ideas because maybe one of them works, but you don’t get a bunch of conditionally independent chances on each one.”
Publisher
Dwarkesh Podcast

36 / evaluation

I’m too stupid to solve alignment and I’m too stupid to execute a handshake with a superintelligence that I told somebody else how to align in a cleverly, deceptive way where that superintelligence ended up in the kind of basin of logical decision theory, handshakes or any number of other methods that I myself am too stupid to a vision because I’m too stupid to solve alignment. The point is — I think about this stuff.

“I’m too stupid to solve alignment and I’m too stupid to execute a handshake with a superintelligence that I told somebody else how to align in a cleverly, deceptive way where that superintelligence ended up in the kind of basin of logical decision theory, handshakes or any number of other methods that I myself am too stupid to a vision because I’m too stupid to solve alignment. The point is — I think about this stuff.”
Publisher
Dwarkesh Podcast

37 / recommendation

Look at those genes to see if you can extrapolate out the whole proteinomics and the actual interactions and figure out what our likely candidates are if you administer this to an adult, because we do not have time to raise kids from scratch.

“Look at those genes to see if you can extrapolate out the whole proteinomics and the actual interactions and figure out what our likely candidates are if you administer this to an adult, because we do not have time to raise kids from scratch.”
Publisher
Dwarkesh Podcast

38 / prediction

At some point you know yourself especially well and you are able to rewrite yourself and at some point there, unless you specifically choose not to, I think that the system crystallizes.

“At some point you know yourself especially well and you are able to rewrite yourself and at some point there, unless you specifically choose not to, I think that the system crystallizes.”
Publisher
Dwarkesh Podcast

39 / evaluation

If you ask me to play a part of somebody who’s quite unlike me, I think there’s some amount of penalty that the character I’m playing gets to his intelligence because I’m secretly back there simulating him.

“If you ask me to play a part of somebody who’s quite unlike me, I think there’s some amount of penalty that the character I’m playing gets to his intelligence because I’m secretly back there simulating him.”
Publisher
Dwarkesh Podcast

40 / recommendation

I could say go study evolutionary biology because evolutionary biology went through a phase of optimism and people naming all the wonderful things they thought that evolutionary biology would cough out, all the wonderful properties that they thought natural selection would imbue into organisms.

“I could say go study evolutionary biology because evolutionary biology went through a phase of optimism and people naming all the wonderful things they thought that evolutionary biology would cough out, all the wonderful properties that they thought natural selection would imbue into organisms.”
Publisher
Dwarkesh Podcast

41 / evaluation

The academic literature would have to be seen to be believed. But the point is the one major technical contribution that I’m proud of, which is not all that precedented and you can look at the literature and see it’s not all that precedented, would in fact have been a way for something that knew about that technical innovation to build a superintelligence that would kill you and extract value itself from that superintelligence in a way that would just completely blindside the literature as it existed prior to that technical contribution.

“The academic literature would have to be seen to be believed. But the point is the one major technical contribution that I’m proud of, which is not all that precedented and you can look at the literature and see it’s not all that precedented, would in fact have been a way for something that knew about that technical innovation to build a superintelligence that would kill you and extract value itself from that superintelligence in a way that would just completely blindside the literature as it existed prior to that technical contribution.”
Publisher
Dwarkesh Podcast

42 / evaluation

If you keep fantasies like that aside, then I think that in the end, even if this world ends up having less time, it was the right thing to do rather than just letting everybody sleepwalk into death and get there a little later.

“If you keep fantasies like that aside, then I think that in the end, even if this world ends up having less time, it was the right thing to do rather than just letting everybody sleepwalk into death and get there a little later.”
Publisher
Dwarkesh Podcast

43 / prediction

I think yes but more abstractly, the steps from the initial accident to the thing that kills everyone will not be understood in the same way.

“I think yes but more abstractly, the steps from the initial accident to the thing that kills everyone will not be understood in the same way.”
Publisher
Dwarkesh Podcast

44 / prediction

Because allegedly, and we will see, people right now are able to appreciate that things are storming ahead a bit faster than the ability to ensure any sort of good outcome for them.

“Because allegedly, and we will see, people right now are able to appreciate that things are storming ahead a bit faster than the ability to ensure any sort of good outcome for them.”
Publisher
Dwarkesh Podcast
Search evidence