Latent Space / 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 / belief
“I think that’s certainly like the domain of, of problems that we’re, that we’re looking to get.”
02 / belief
“I think the reason why post-training is a place where this makes a lot of sense is a lot of what we’re talking about is surgical edits.”
03 / recommendation
“You were very excited because I read Ted Chiang over the holidays and I was very inspired by this short story called Understand, which apparently is, like, pretty old.”
04 / belief
“I think scale allows you to learn a lot of information and, and reduce noise across, you know, large amounts of data.”
05 / belief
“I think engineers are sorely wanted for interpretability as well, especially at Goodfire, but elsewhere, as it does scale up.”
06 / belief
“I think for us, it’s like, we have a very grounded view of alignment and, and safety in that we want to make sure that we can build models that do what we want them to do and that we have scalable oversight into what these models are doing.”
07 / belief
“For other people who want to get started, I think, you know, MATS is a great program.”
08 / belief
“I think he’s the one who coined the term of LLMs as, like, a blurry JPEG of the internet.”
09 / belief
“I think for me, one way in which I think about world models is just like this, like, having this consistent model of the world where everything that you generate operates within the rules of that world.”
10 / belief
“There’s a lot of models that work in, like, pixel space, as we call it. So if you’re doing world models, video models, even robotics, where there’s not a very clean natural language interface to interact with, I think we think that Interp can really help and are looking for a few partners in that space.”
11 / evaluation
“I think that while it’s not clear what the product is at the end of the day, it’s clearly very valuable.”
12 / evaluation
“I think the main sort of point here that I think is exciting is that there’s not a whole lot of inter being applied to models quite at this scale.”
13 / evaluation
“Because yeah, it’s just like some worrying research that’s out there that shows, you know, we really don’t know what’s going on.”
14 / prediction
“You really predicted a project we’re already working on right now, which is detecting hallucinations using interpretability techniques. And this is interesting because hallucinations is something that’s very hard to detect.”
15 / evaluation
“Honestly, I think the biggest thing that this highlights is that as we’ve been growing as a company and taking on kind of more and more ambitious versions of interpretability related problems, a lot of that comes to scaling up in various different forms.”
16 / evaluation
“Okay, great. So I think like one, just to kick off, it’s a very interesting role to be head of product, right?”
17 / preference
“But I think we also sort of see some of the goals as even more broader as, as almost like the science of deep learning and just taking a not black box approach to kind of any part of the like AI development life cycle, whether that. That means using interp for like data curation while you’re training your model or for understanding what happened during post-training or for the, you know, understanding activations and sort of internal representations, what is in there semantically.”
18 / evaluation
“A lot of my time as as head of product, I think product is a bit of a weird role these days, but a lot of it is thinking about how do we take our frontier research and really apply it to the most important real world problems and how does that then translate into a platform that’s repeatable or a product and working across, you know, the engineering and research teams to make that happen and also communicating to the world?”
19 / evaluation
“I also think to your point, it’s been really, really inspiring to see, I think a lot of young people getting interested in interpretability, actually not just young people also like scientists to have been, you know, experts in physics for many years and in biology or things like this, um, transitioning into interp, because the barrier of, of what’s now interp.”
20 / evaluation
“I think there are many, many things they’re useful for, but we have definitely run into cases where I think the concept space described by SAEs is not as clean and accurate as we would expect it to be for actual like real world downstream performance metrics.”