flâneur

Architecture Research as Addressing Constraints to Scaling

beren.io · 3,258 words · saved by 1 readers

Author’s note: Short note. Really a quick extension to scaling is subtler than it seems. This is probably obvious to many but still worth writing, I think/hope. Sometimes when I talk to people about architecture research, they have a somewhat naive impression that it is mostly about empirically searching to...

Author’s note: Short note. Really a quick extension to scaling is subtler than it seems. This is probably obvious to many but still worth writing, I think/hope. Sometimes when I talk to people about architecture research, they have a somewhat naive impression that it is mostly about empirically searching to find tweaks that lower loss/perplexity a small amount. E.g. we try adding a layernorm here or there or changing this activation function or adding a convolution layer or whatever, and just trying to improve loss. This is often coupled with the idea that LLM architecture research is…

saved by

related reading