Eve Bodnia

So the way if somebody would tell me and I were an engineer how to design such robots,

I would say, okay, what kind of data we have available?

We have probably the language part, which is, you know, people talking to me.

And we also have the visual part.

We also have sensors measuring the distance, how far you are from things.

You probably have like an input from like overall environment around you.

So you can adopt your behavior and you're like moving your body around.

So you can have a bunch of input information out here and you also have a purpose.

So what kind of robot is it?

Is it going to be, I don't know, your house cleaner or something else?

So the purpose is going to define how much and what kind of interaction you're going to have.

So if it's a robot who is taking care of a sick person and this person just leaves themselves and they don't have a caregiver,

So they're going to have a set of routines and they probably should be communicated using language, but it's also, they should be having ability to like evaluate what's around them.

Is this person in danger?

Should I call 911?

You know what I mean?

It depends on the purpose.

So this is why it's important to have all of these ingredients in place and be combined in the way and making sure it's functioning the way it's meant to be.

So LLM alone cannot do this.

And it's also like very expensive.