Public evidence record
Published podcast speaker
Claim ledger
9 transcript-backed records
01 / belief
“I think scale allows you to learn a lot of information and, and reduce noise across, you know, large amounts of data.”
02 / 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.”
03 / belief
“For other people who want to get started, I think, you know, MATS is a great program.”
04 / 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.”
05 / evaluation
“I think that while it’s not clear what the product is at the end of the day, it’s clearly very valuable.”
06 / 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.”
07 / 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?”
08 / 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.”
09 / 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.”