The issue remains the context window. I haven't seem any example of a "memories" system that the agent can update over time without it devolving into slop. The magic of the human brain is that we seem to have decently sophisticated heuristics parsing/saving memories as well as for letting memories that aren't accessed decay.
Yes i agree, but somehow knowledge got put into the LLMs head during train time, but why does it not work during inference time? Too little examples? Do llms know stuff with exactly one occurence in the training data?
It's like that all that knowledge exists as a vague memory. I've found if I ask them specifics about any book I've read (w/o allowing tool calling), when they get it wrong their hallucinating things that are often correct or wrong in subtle ways. Are they're just completely out of pocket.
It depends on what you mean by continual learning. Do you just mean some form of memorization, or something more/different?
I mean it gains the same level of expertise as it does on stuff in training data.
The issue remains the context window. I haven't seem any example of a "memories" system that the agent can update over time without it devolving into slop. The magic of the human brain is that we seem to have decently sophisticated heuristics parsing/saving memories as well as for letting memories that aren't accessed decay.
Yes i agree, but somehow knowledge got put into the LLMs head during train time, but why does it not work during inference time? Too little examples? Do llms know stuff with exactly one occurence in the training data?
It's like that all that knowledge exists as a vague memory. I've found if I ask them specifics about any book I've read (w/o allowing tool calling), when they get it wrong their hallucinating things that are often correct or wrong in subtle ways. Are they're just completely out of pocket.
my initials = LLM :(