Invest with AI
00:15:15 · Doug Clinton
[00:15:15] S0: Yeah, I think it's probably still an open question. For us, I mean, we use various MCP, you know, sources that help us pull in some data. And I think that... I think the world broadly is evolving to this idea that getting context to the models at the right time and the right place is super valuable. Right? And you look at, like, a CarbonArc, right, paying paying almost per piece of data, and you get to determine what you think is really valuable. I think we're gonna see a lot more models like that. And and whether it literally uses, you know, the MCP, that exact protocol, or if it just looks like an API or whatever, I don't know how much that matters relative to having just the right structures, the right payment models, and ultimately, right data sources and the right ability for the models to say, I need this piece of data. I think that's the super valuable piece. And I would say this, like, models today are... I think they're pretty good. If I had to grade them, I'd give them, like, a b plus as an analyst sort of understanding, like, this is the thing that's probably gonna move a stock in a given quarter. Their creativity isn't quite there like a human analyst. I mean, some of the creative things I've heard for human analysts doing over the years to try to get an angle on a quarter are incredible. But, again, think about the future. Think about a year from now. Think about two years from now. I think models will think of those super creative things and be figuring those things out for us. And that's the frontier that I'm really interested in trying to figure out.
00:16:55 · Khe Hy
[00:16:55] S1: Doug, when we, before we started recording, you had mentioned the importance of knowledge graphs as it relates to MCP. Could you say a little bit more about that?
00:17:06 · Doug Clinton
[00:17:06] S0: Yeah. The... It's it's funny, Kaye. Like, the the terms, as you as you mentioned earlier, right, have have sort of evolved in, like, what is the hot thing at AI? I mean, it changes every six months ish or so, it feels like. And I would say this this concept of sort of the knowledge graph feels like very much the frontier right now and just trying to figure out, you know, how do you take all of the knowledge that you have as an organization or as an investment team or whatever your your your node structure is and make that entire graph usable by every agent that you have running on your platform. Right? And that may be hundreds of agents or thousands of agents depending on how evolved you are. But it's a really complex task to let... I mean, imagine thousands of different agents trying to pull different bits of context real time, creating new context, right, that other agents should then have access to. Doing that really well, I think, is going to be a source of alpha for people using language models or just agents in general, I think, to invest probably over the next... I'd give it twelve to eighteen months. I think that'll be a huge advantage before eventually it probably becomes a little bit more commoditized, whether that's because some third party vendor introduces a really easy to use system, which just doesn't exist right now that I've seen, Or, right, Claude code and codex make it so easy to just say, hey. Implement this, and it just works.
00:18:38 · Khe Hy
[00:18:38] S1: It's fascinating too because the... Sorry, Brett. The... Like schemas and ontologies, again, these kinds of buzzwords that no one was talking about six months ago, but it is this weird idea that you have this data, but you have this structure that oftentimes is just intuited by your process, by your analysts, by your PMs, by the industry. And that might be the gray matter that the LLM hasn't figured out yet. And just like watching the race to disentangle that, to categorize that, to label that, to, you know, to make it visible is just it's just really fascinating right now. And I guess probably early days to know if it's even effective.
00:19:25 · Doug Clinton
[00:19:25] S0: I think so. And it comes back to this idea of taste. You know, you hear the word taste often in AI, which I think is sort of this nod to longer term human value, this sort of instinct that we've talked about. I do think to some extent, like, creating these ontologies and these knowledge graphs, there is an element of, okay. Fine. Like, codex, point it at something, give it a really great creative loop, and it'll probably figure something out that's passable. But to make it a plus, I think it does need to have that element of taste from a human who really understands, like, this is what it means to generate alpha, not just, like, what the Internet has taught you as an AI model, but, like, this is why it's hard. Right? And this is kind of, like, maybe even the history of how how alpha sort of evolves in in a sense. And being able to take that taste and apply that to the ontology, that's where I think you get this unique value from humans coming in and taking sort of AI's baseline work, which is like B plus and then getting it up to that A level. And that's where I think you can really get some additional value from it.
00:20:30 · Brett Caughran
[00:20:30] S2: Could we drill into this this concept of knowledge graph a little bit more? Like, what does it actually look like in practice? I'd be curious, Kay, your perspective on like, what's the what's the sort of zero to one? Like, if a client comes in and wants to build a knowledge graph, what does that mean? Is that internal file structure? How do I get my data out of Excel files and OneNotes and PDFs and Outlook inbox and Slack? Like how do you, what's that actual process look like?