alt Hacker NewsThere's only so far engineers can optimise the underlying transformer technique, which is and always has been doing all the heavy lifting in the recent ai boom. It's going to take another genius to move this forward. We might see improvements here and there but the magnitudes of the data and vram requirements I don't think will change significantly
Replies
aerhardt • last Friday at 9:12 PM
I’ve read and heard from Semi Analysis and other best-in-class analysts that the amount of software optimizations possible up and down the stack is staggering…
How do you explain that capabilities being equal, the cost per token is going down dramatically?
➕ show 1 reply
State space models are already being combined with transformers to form new hybrid models. The state-space part of the architecture is weaker in retrieving information from context (can't find a needle in the haystack as context gets longer, the details effectively get compressed away as everything has to fit in a fixed size) but computationally it's quite strong, O(N) not O(N^2).