High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Kenneth Stanley

Published podcast speaker

Claims
14
Episodes
2
Shows
1
Named items
0

Claim ledger

What Kenneth said.

14 transcript-backed records

01 / belief

I think 1 of the really interesting things about the observation in this paper is it pokes a hole, I think, in a very deep assumption that we have that if the results are good, then what's underneath the hood is also good.

“I think 1 of the really interesting things about the observation in this paper is it pokes a hole, I think, in a very deep assumption that we have that if the results are good, then what's underneath the hood is also good.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

02 / belief

Like like, I think, you know, it's interesting, like, in the field of AI that if you go back 10 years or so, like, most of the interactions of AIs with dynamic training environments would be in simulations.

“Like like, I think, you know, it's interesting, like, in the field of AI that if you go back 10 years or so, like, most of the interactions of AIs with dynamic training environments would be in simulations.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

04 / belief

Like, you know, we we think about, you know, when you say, like, eventually, if you experience enough of the world, like you say, of course, you might expect that your representation start to mirror just the way that the world is.

“Like, you know, we we think about, you know, when you say, like, eventually, if you experience enough of the world, like you say, of course, you might expect that your representation start to mirror just the way that the world is.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

05 / belief

I mean, 1 of the really important points I wanna add to this, this may also apply to humans. So I don't want to seem like I'm saying that all humans have unbelievably beautiful, unfractured We also, I think, victims of going through things in a bad order sometimes.

“I mean, 1 of the really important points I wanna add to this, this may also apply to humans. So I don't want to seem like I'm saying that all humans have unbelievably beautiful, unfractured We also, I think, victims of going through things in a bad order sometimes.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

06 / belief

You could say, this is good enough, I'm happy. But I think in terms of what we can't do because of that, that we might someday in the future be able to do, The things we can't do are the things where the human mind isn't having the ideas.

“You could say, this is good enough, I'm happy. But I think in terms of what we can't do because of that, that we might someday in the future be able to do, The things we can't do are the things where the human mind isn't having the ideas.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

07 / belief

I suspect it has more implications than just that because when we go beyond efficiency to things like creativity, what you're seeing is that the dimensions that have been discovered in the skull for example, align with new skulls, imagining new things in the world.

“I suspect it has more implications than just that because when we go beyond efficiency to things like creativity, what you're seeing is that the dimensions that have been discovered in the skull for example, align with new skulls, imagining new things in the world.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

08 / belief

Like, what are you objecting to? But the but the point is that it can still be an impostor because it's like what we care about here is not just that it's going to get answers right, like get good test scores, like seem to be plausibly human when you talk about things that are in distribution.

“Like, what are you objecting to? But the but the point is that it can still be an impostor because it's like what we care about here is not just that it's going to get answers right, like get good test scores, like seem to be plausibly human when you talk about things that are in distribution.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

09 / evaluation

We also show new examples. But you you know, the word reason I use the word indirect is because unlike these pick breeder images, we can't just go in and look at a neuron and know what it does explicitly because that's what's so nice about pick breeder images because they're 2 d.

“We also show new examples. But you you know, the word reason I use the word indirect is because unlike these pick breeder images, we can't just go in and look at a neuron and know what it does explicitly because that's what's so nice about pick breeder images because they're 2 d.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

10 / uncertainty

It could be though something implicit and indirect. And so I think I think overall, it's it's like Akash said, there's still some unknowns here about what actually what actually matters, what doesn't matter, especially with respect to the representation.

“It could be though something implicit and indirect. And so I think I think overall, it's it's like Akash said, there's still some unknowns here about what actually what actually matters, what doesn't matter, especially with respect to the representation.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

11 / evaluation

It's just emergent from how SGD climbs these gradients. But the thing that I think makes this really intriguing, the reason that the paper is because beyond just that, is that it gives you something that otherwise could never exist, which is a counterexample, that there actually do exist networks that don't have that issue.

“It's just emergent from how SGD climbs these gradients. But the thing that I think makes this really intriguing, the reason that the paper is because beyond just that, is that it gives you something that otherwise could never exist, which is a counterexample, that there actually do exist networks that don't have that issue.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

12 / prediction

If you have an algorithm that's trying to follow a gradient by matching closer and closer and closer to the objective, getting a higher and higher score, you're going to get stuck in a dead end because of deception, because the things that lead to the thing you want actually don't look like the thing you want.

“If you have an algorithm that's trying to follow a gradient by matching closer and closer and closer to the objective, getting a higher and higher score, you're going to get stuck in a dead end because of deception, because the things that lead to the thing you want actually don't look like the thing you want.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

13 / evaluation

Like, what are you objecting to? But they but the point is that it can still be an impostor because it's like, what we care about here is not just that it's going to get answers right, like, good test scores, like, seem to be plausibly human when you talk about things that are in distribution.

“Like, what are you objecting to? But they but the point is that it can still be an impostor because it's like, what we care about here is not just that it's going to get answers right, like, good test scores, like, seem to be plausibly human when you talk about things that are in distribution.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk

14 / evaluation

The thing that I think makes this really intriguing is that it gives you something that otherwise could never exist, which is a counterexample that there actually do exist networks that don't have that issue.

“The thing that I think makes this really intriguing is that it gives you something that otherwise could never exist, which is a counterexample that there actually do exist networks that don't have that issue.”
Speaker
Kenneth Stanley
Publisher
Machine Learning Street Talk
Search evidence