Karthik Narasimhan on autonomous agents and multi-agent interaction

Transcript

What do you think multi agent interaction is? I mean, if you take a really, really high level view, multi agent interaction is basically like essential for AGI, right? We're all doing multi agent interactions now, right? We're all agents, right? So you so in one sense, like if you want. Agents to be close to this level of intelligence, they need to be able to handle multi agent interactions, right? But to be able to go down a bit more, you know, concrete, right. I think of it as like. The you always want to have some kind of asymmetry between different agents for it to be truly multi agent, right? So it's just like you take. I mean, you could even consider the prompt of two different agents to be, you know, different, but that's like it, it's a little bit shallow, right? So you basically have the same model underlying and you just like prompted them in different ways. I think cases where it could make more sense are, you know, there's like some kind of knowledge asymmetry. Let's say you know, you have two robots and you know, 1 is in one corner of the world gathering some input sensors and 1 is in the other corner and they do something. Or in the more like less physical sense you could even imagine. You know, places where information is just like sort of guarded due to privacy concerns or let's say like different companies have their own siloed information, but you want agents between them to be interacting with each other. That's when like you truly need, you know, the protocols for agents to communicate and like figure out how they want to work together and all of that.