Bronson Schoen: belief

Transcript context

…think well, I'd I'd done the numbers. So when talking with you, it's teen times longer than if you took every episode of Cognitive Revolution ever and transcribed it and played them back to back. And it's like, to summarize those incidents, you can pick out individual sentences, but it's very hard to pull together kind of a a linear narrative exactly what happened. And it's very hard to just read through. I think someone it's very possible that some of the UKAC might either take or has the title of reading the most caught just because they've had to go through these traces. There's a very funny part in the incident report where they're yes. We have the models identify the important parts, and the model identified this enormous amount to read. And I think one of the the difficulties is going to be, like, we're relying more and more on models to do this summarization. But I think as can be seen with some of the OpenAI examples, a lot of this stuff can be, like, weird or subtle or hard to find to pull apart. And the the models doing the summarizing, I think, often aren't giving either that amount of permission or don't necessarily have the the capability. There's some degree of taste would be, like, too high. I'm kinda bar for it. There's some degree of you're looking for weird and strange things in the the chain of thought. Yeah. And I think these are very difficult. I one of the things that you're seeing especially is for some of the the recent cryptography stuff from Anthropic. They had mentioned that, like, the the actual work done by the model was, a week, but, like, the verification time was, like, two months or whatever. It's like I might be getting the numbers wrong, but it's just understanding like what the model's doing, especially as the models are doing domains that like require just a bunch of expertise to understand. Like understanding the chain of thoughts for the like groundbreaking math stuff must just be, like, incredibly difficult. Not even out of, like, the model's obfuscating it. Just out of it's, a very hard subject. You have to have a lot of expertise. If the model was, like, doing reasoning about other things in between, it's, like, very hard to have an incriminating aspect of it. Yeah. I I…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.