High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Robert Lange

Published podcast speaker

Claims
14
Episodes
1
Shows
1
Named items
0

Claim ledger

What Robert said.

4 transcript-backed records

01 / evaluation

And I think language models with the right sort of evolutionary hardness are extremely powerful in terms of scaling up to to to make discoveries. And, yeah, I think Jeremy as well as the AlphaEvolve paper as well as sort of work we've done on, like, the Daven Gudel machine, for example, shows that this sort of stepping stone accumulation plus iterative verification and collecting sort of information and evidence from the real world real synthetic evaluator is really important for that.

“And I think language models with the right sort of evolutionary hardness are extremely powerful in terms of scaling up to to to make discoveries. And, yeah, I think Jeremy as well as the AlphaEvolve paper as well as sort of work we've done on, like, the Daven Gudel machine, for example, shows that this sort of stepping stone accumulation plus iterative verification and collecting sort of information and evidence from the real world real synthetic evaluator is really important for that.”
Speaker
Robert Lange
Publisher
Machine Learning Street Talk

02 / evaluation

Right? And I think, actually, like, even though, like, large frontier language models are extreme, like, let's say, black boxes or it's very hard to get a full mechanistic understanding of them, the outputs can be.

“Right? And I think, actually, like, even though, like, large frontier language models are extreme, like, let's say, black boxes or it's very hard to get a full mechanistic understanding of them, the outputs can be.”
Speaker
Robert Lange
Publisher
Machine Learning Street Talk

03 / evaluation

I think 1 thing that was very interesting about the circle packing problem, sort of also coming back to the problem problem that I discussed initially was that originally, we we used a formulation where the correctness is checked with, like, a very tiny amount of slack.

“I think 1 thing that was very interesting about the circle packing problem, sort of also coming back to the problem problem that I discussed initially was that originally, we we used a formulation where the correctness is checked with, like, a very tiny amount of slack.”
Speaker
Robert Lange
Publisher
Machine Learning Street Talk

04 / evaluation

It could it could in fact happen. But I think, like, for all of these things, we started out sort of with the, let's say, most intuitive algorithmic component that we had, and UCB was 1 that really did the job here.

“It could it could in fact happen. But I think, like, for all of these things, we started out sort of with the, let's say, most intuitive algorithmic component that we had, and UCB was 1 that really did the job here.”
Speaker
Robert Lange
Publisher
Machine Learning Street Talk
Search evidence