Public evidence record
Published podcast speaker
Claim ledger
7 transcript-backed 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 / belief
“I think engineers are sorely wanted for interpretability as well, especially at Goodfire, but elsewhere, as it does scale up.”
04 / belief
“I think he’s the one who coined the term of LLMs as, like, a blurry JPEG of the internet.”
05 / 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.”
06 / 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.”
07 / 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.”