We need chips that have this kind of particular ineffable property, which is incredibly high bandwidth to memory so we can load the weights, we can load the state many thousands of times per second, but also have like economical memory. Because when you look at what it looks like to run inference at data center scale for thousands of users, the economics actually collapse down to essentially a kind of cost per gigabyte of the memory that you're employing. and so that's been the sort of other key focus for us is unlocking this kind of fundamentally new building block, which is finding a path to get aggressively high bandwidth from this kind of from the world's lower-cost memory, DRAM memory.
← 2 October 2026No Priors
Frontier Chips for Frontier AI Labs, with Walter Goodwin, Founder/CEO of Fractile
Walter Goodwin argues frontier AI inference needs chips with very high memory bandwidth and affordable capacity, built by lean full-stack teams that iterate fast, since frontier labs cannot safely bet alone on proprietary silicon.
Watch on YouTube ↗Word for word
To bring it back to the workloads we're excited about as well: a lot of hard problems in the world look a bit like this, where there is a lot of thinking that can now be automated. There's a lot of cerebral work, but then there is also this intrinsic latency to something that you do. I think we see this in AI for guiding AI model development today. So, the RSI work: yes, we can now have extreme intelligence that is guiding our experiments, but now we're just experiment bottlenecked, we're compute time bottlenecked.
Do more with Charlie
Analyze any YouTube videoPaste a link — get its key points and best quotes in minutes. 10 videos a day.Paste a YouTube link →Your own podcast feedAdd up to 10 YouTube channels you follow. Charlie reads their new episodes for you.Add your channels →
Free — sign in with your email, no password.