[Wetime]

This paper show a new tool called Galahad.Normally, AI has to think and guess the answer every time, which costs time and money.

The knowledge of the model grows next to it not the model itself and no it is not the same as cache

No fine-tuning needed

It gives the exact same right answer every time, costs zero extra tokens, and saves lots of energy

[flowerbreeze]

Maybe it all works, but the paper is not trivial to decipher and the GitHub repository does not seem to exist. It doesn't seem to define what are the inputs to the system (what is a query? UTF-8 text? tokens?) and what are the outputs. It'd really help if the algorithm was written out step by step with all the expected type information included.

At first I thought it was similar to something I've built before as a long-term slowly degrading cache for augmenting an FFN by caching well-learned answers, answering by performing a beam search in the key space resulting in located key accuracy measure (how well it corresponds to the input query) and answer confidence (has it been a long time since verification?), but that's not quite it? It feels similar in some way, but is it?

[SwellJoe]

So, you don't know what it is, either.

[Wetime]

We handeld llm like a human brain we decopelled knowledge from the memory and build a memory layer that makes redoing things free and fast, so the llm can once it learned something solves it for free the next time

[saidnooneever]

this sounds like ur explaining caching

[SwellJoe]

Sounds like they're explaining magic. Because current models cannot learn and they cannot remember.

[saidnooneever]

there is RL for LLMs which actually changes the weights but its more specialization than learning and wont counter the probabalistic nature of the thing

[SwellJoe]

Training is not something you can just bolt on, and it generally requires even larger hardware than inference for a given model, and a huge amount of time. If you're aiming for "free", a OP claims, RL aint it.

[saidnooneever]

how is it not the same as a cache it its exact description matches the description of a cache?

[Wetime]

A cache remembers answers (only useful for the exact same question again). We remember the proven method and redo the work on every new question, so it solves ones it's never seen, which a cache simply can't.