[swax]

Sometimes I'll tell two agents very explicitly to share the work, "you work on this, the other should work on that." And one of the agents ends up delegating all their work to the other, constantly asking for updates, coming up with more dumb ideas to pile on to the other agent who doesn't have time to do anything productive given the flood of requests.

What we should do is train AI on self-help books like the '7 habits of highly productive people'. Let's see how many paperclips we get out of that.

[nerdponx]

I suspect it's a matter of context: one or both agents forget that they're supposed to be delegating. ChatGPT's "memory" system for example is a workaround, but even then it loses track of details in long chats.

[swax]

Opus seems to be much better at that. Probably why it’s so much more expensive. AI companies have to balance costs. I wonder if the public has even seen the most powerful, full fidelity models, or if they are too expensive to run.

[nerdponx]

Right, but this is also a core limitation in the transformer architecture. You only have very short-term memory (context) and very long-term memory (fixed parameters). Real minds have a lot more flexibility in how they store and connect pieces of information. I suspect that further progress towards something AGI-like might require more "layers" of knowledge than just those two.

When I read a book, for example, I do not keep all of it in my short-term working memory, but I also don't entirely forget what I read at the beginning by the time I get to the end: it's something in between. More layered forms of memory would probably allow us to return to smaller context windows.

[swax]

I mean we have contexts now so large it dwarfs human short term memory right?

And then in terms of reading a book, a model's training could be updated with the book, right?