alt Hacker NewsI am sorry but the whole "biological memory" thing seems like marketing fluff on basic cache mechanisms.
You said it cuts token usage by 84% but isn't that typical for any typical chunked RAG system?
And why did you specifically chose to test against the LoMoCo dataset when there's a lot of issues with it and it being very easy to cheat?
Replies
jnovek • yesterday at 9:28 PM
I think it’s reasonable, a forgetting curve is intended to models a biological process.
And a neural network is really just a composed, non-linear parameterized function that maps input vectors to output vectors. Sometimes metaphors or analogies do contribute something valuable.