Zero-Shot Learning
00:49:36 · Nancy Wang, Dev Tagare, Adarsh Hiremath
[00:49:36] S3: So what would that actually look like? Just a set of instruction sets? [00:49:40] S1: Or A set of skills and tools effectively. Yeah. And then, like, a general arbiter of picking skills and tools and bootstrapping what we think... What what we call agents today effectively. But, like, there's no random goal driven thing anymore. It's all evals driven. Evals inform trajectories. Models are able to keep the task on a trajectory. [00:50:02] S2: I mean, I would say that I largely agree with that, where even if you just take the agent to agent interaction out of the picture, I think one of the things that people told about agents that was kind of incorrect is that it's a unidirectional thing between humans and agents. You give the agent the task, it just does it. It's very much bidirectional. Right? The human gives the agent the task. It needs the human feedback to understand what good looks like, not make mistakes, all the things that we've talked about. And I think the natural progression of that is the bidirectional, you know, collaboration model agents, where an agent will need to talk to another agent, it will need to orchestrate with another agent, it will need to oversee the output of another agent's work. And I think that's certainly something that'll happen in twelve to eighteen months. [00:50:41] S1: I mean, like, it's it's effectively becoming a three way handshake between the the human set of agents and maybe the model as a separate category. And the models are more a constellation of models versus a single model.
00:50:41 · Dev Tagare, Nancy Wang, Adarsh Hiremath
[00:50:41] S1: I mean, like, it's it's effectively becoming a three way handshake between the the human set of agents and maybe the model as a separate category. And the models are more a constellation of models versus a single model. [00:50:55] S3: Or a mixture of experts. [00:50:56] S1: Mixture of experts. Yeah. Yeah. Yeah. So, yeah, that's where I I think, like, 2026 in my mind is the year of the model again. [00:51:03] S2: Right. [00:51:04] S1: '25 was probably the year of the agents and the and the swarms, if you will. We'll see. [00:51:09] S3: Yeah. Let... Let's revisit that prediction in December. [00:51:12] S1: Quite likely going to be wrong, given how things are evolving, but we'll see. [00:51:16] S3: And we also love to end the episode on the question of, if you had, let's say, a month to build anything you wanted, it could be mercur, it could also be, you know, something completely different, what would that be? [00:51:29] S2: I feel like I I have to I have to say mercur in part because it's true and because I have an obligation for it to be mercur. But, you know, one of the things that I wish, I I could spend some time on is just random side projects. Right? It just... You can't help but, you know, walk around and and just to have, like, ideas pop in your head with the with the pace at which things are are evolving. So, you know, I think maybe a little bit of a Sunday here and there, I'll I'll I'll make some time to to build out some some projects. [00:51:58] S3: Awesome. I'd love to showcase one on our episode.
00:51:58 · Nancy Wang, Dev Tagare, Adarsh Hiremath
[00:51:58] S3: Awesome. I'd love to showcase one on our episode. [00:52:01] S1: Let's do it. Yeah. Yeah. Thank you, Adarsh. Appreciate the time. This is a lovely conversation. Really appreciate [00:52:05] S2: it. Thank you for having me. [00:52:06] S3: Going for hours. [00:52:07] S1: Yeah. Thank you.