Machine Learning Street Talk / episode intelligence
Speakers in the public record
Claim mix
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
20 published records
01 / evaluation
“No one's using the XLSTM. Not many people are using Mamba because why not? All you need to do is just scale the transformer as much as possible.”
02 / belief
“To a large extent, I suspect that there are ways around that that are related to how it is that like your AI coding agent actually works.”
03 / commitment
“We will be you could say, yeah, we're gonna use diffusion models if you're make me roll my eyes and say that.”
04 / belief
“Now I can't act in the world of my mind, but it seems macroscopically intelligible. We think about our minds.”
05 / belief
“Yeah. But I think that's, I mean, those systems are very interesting because it is remarkable that really dumb simple rules, right, can lead to like really interesting sophisticated behavior.”
06 / belief
“Grounded in the domain in which in which we are grounded as a route to to creating, you know, AI, you know, an AI models that in fact think like we think.”
07 / commitment
“What I will say instead is that is that the the additional constraint that we're imposing, it's not just about objects, it's also about their relationships.”
08 / belief
“Some of the programs which are learned are just really complicated. They had examples of like I think drawing towers and drawing graphs and stuff like that.”
09 / belief
“You can apply, you know, and just sort of, and and, know, wrote a series. This is 1 of the reasons I think he's so prolific is because he's basically, you know, written variations on the same paper, right, but just applied in different domains.”
10 / belief
“The same sort of thing, you know, goes with, you know you know, I I think the sort of converse of that is what's going on here.”
11 / evaluation
“You've 1 of the things that's critical a critical aspect of the way we think about the world and the way we learn about the world is is that it's continual and it's interactivist.”
12 / evaluation
“It's being used to track these sort of low level statistics that that we sometimes need, but don't always need. And so this is why I say that that, like, you know, when we say context matters, you know, you can think of that in terms of, we were able to flexibly switch between tasks, which means having a lot of resources and having a lot, you know, maintained and having them still be in good working order just in case we need them.”
13 / preference
“There's the work, you know, I mean, I've been using I've been using like natural gradient methods for a very long time, which allow you to like massively speed up gradient inference and in some situations completely eliminate the need to do gradient inference and instead like, you know, do coordinate descent and allowing you to take massive jumps in parameter space and not actually lose the the ability to do learning of sophisticated model in in a sophisticated modeling scenario.”
14 / recommendation
“They have this sparse causal macroscopic structure to it. And so should our models and so should and and and the only way to do that is not just to like put a robot in the real world, but to put a robot with a model that is structured in that fashion into the real world.”
15 / preference
“We care about the causal relationships at the macroscopic level because that is where we live.”
16 / preference
“The more tightly linked your actions or your affordances are to the things that causally impact the world, the more effective those actions are with respect to your model, but hopefully also with respect to reality. And so we prefer causal models, you know, in part because they are relative, you know, relatively speaking simpler to execute, right, in in in a simulation form, but also because they they point directly to, well, where should I intervene?”
17 / prediction
“I actually the reason why I say transformer comes with an asterisk is because a lot of the things that transformers have been that that people believe that the transformer enabled, I think really resulted more from scaling.”
18 / commitment
“Is we wanna is is we're focused on building cognitively inspired models that are based on our understand on on the way the world in which we live actually works because we believe intelligence must be embodied.”
19 / evaluation
“Now we have to like be super careful with our words. They're relatively optimal because they're not actually using a 100% of the information that the computer like your the visual information that you use, you don't use a 100% of the information that the computer provided you.”
20 / evaluation
“Certainly if you wanna have models that think the way we think. And that that got lost in the shuffle, and we're starting to see, you know, as as as we're starting to see the limitations and the faults and flaws of of of these approaches, and starting to see them not living up to the hype, which I think is like now it's standard that like like AGI is no longer I don't know if you read the other day, at least according to, you know, the experts in the field at the top of the best companies in the business, like AGI is no longer, like, a huge priority.”