00:23:47 · Matt Stockton, Brett Caughran
Like, that's actually 80% of the work is describing your intent clearly, right? [00:23:53] S0: Which is challenging for many investors because so many investors are these sort of intuitive, almost like concert pianists. Like they sort of can create a masterful trade, but asking them to sort of turn around and write an 80 page operating manual of sort of how they make decisions is a much harder exercise. How do you think we crack that? Yeah. That disambiguation because specificity is really critical to sort of overcome the sarcastic nature of the underlying models, right?
00:23:53 · Brett Caughran, Matt Stockton
[00:23:53] S0: Which is challenging for many investors because so many investors are these sort of intuitive, almost like concert pianists. Like they sort of can create a masterful trade, but asking them to sort of turn around and write an 80 page operating manual of sort of how they make decisions is a much harder exercise. How do you think we crack that? Yeah. That disambiguation because specificity is really critical to sort of overcome the sarcastic nature of the underlying models, right? [00:24:32] S1: Yeah, yeah. So my biggest hack or view for this is it turns out like the models are actually helpful to help extract this information from you, right? So like one of the biggest ways that I use these tools, I'm trying to build something or describe what I want, is I will truly take a voice memo of me just like talking, right, extensively, maybe go on a run and just record myself talking if I have to build a project. And like, I'm not even... I'm truly just rambling my thoughts, right? Because it turns out if you take that voice memo and turn it into a transcript and load it into a tool like Cloud Code and do something like, Hey, here's where I'm at with this idea or this thing I need to do. Want you to ask me questions exhaustively until you're clear on what I'm trying to do, and that's a complete story. So you can actually use these tools, right, to kind of help you you build that. Like, you don't have to start from a blank slate. So that's kind of my view on how I get this information out on paper.
00:24:32 · Matt Stockton, Khe Hy
[00:24:32] S1: Yeah, yeah. So my biggest hack or view for this is it turns out like the models are actually helpful to help extract this information from you, right? So like one of the biggest ways that I use these tools, I'm trying to build something or describe what I want, is I will truly take a voice memo of me just like talking, right, extensively, maybe go on a run and just record myself talking if I have to build a project. And like, I'm not even... I'm truly just rambling my thoughts, right? Because it turns out if you take that voice memo and turn it into a transcript and load it into a tool like Cloud Code and do something like, Hey, here's where I'm at with this idea or this thing I need to do. Want you to ask me questions exhaustively until you're clear on what I'm trying to do, and that's a complete story. So you can actually use these tools, right, to kind of help you you build that. Like, you don't have to start from a blank slate. So that's kind of my view on how I get this information out on paper. [00:25:46] S2: It's interesting because we've spoken about, you used an analogy, Brett, of, you know, a pianist and intuitive pianist. I saw this quote, I can't remember who said it, but it's basic... Oh, Daniel Meisler. He said, All of knowledge work is just vibes and spreadsheets. Right? [00:26:05] S1: And LMs don't do well
00:26:05 · Matt Stockton, Khe Hy
[00:26:05] S1: And LMs don't do well [00:26:06] S2: with vibes, right? Like, want instructions and they want intent. And it's funny because Matt and I have spoken to different companies, just discovery work. At the end, they just think you just throw all this data in an LLM and then it's magic wand waves and, like, every answer you could ever want is there for you. But the reality is, as Matt and you are both alluding to, is that you have to, like, understand what output you're trying to get. And that is actually not even a tech question. In fact, the tech makes the need for this process documentation or process mapping way more important than it ever has been. And I'll be curious to see how financial services people do with that because especially investment on the investment side, notoriously don't really care much about that. They have their process. Their process works. Let's call it a day. And so, don't know if either of you have thoughts on like, are people ready to sit in a room with Matt for four hours and be like, so tell me when this piece of information comes out, what are the seven things you do and the three things that you think about?
00:27:24 · Brett Caughran, Matt Stockton
[00:27:24] S0: It's sort of become the singular focus of almost singular focus of the consulting we're doing, just helping people map that. We've built a map of sort of what we view as a style agnostic fundamental investing process into 800 sort of primitive subatomic steps to sort of show a salad bar, if you will, of the various steps to sort of inspire, help people address that blank page problem. But it is hard. There's such a combinatorial complexity of what investors do because the way a multi manager utilities analyst approaches his or her day versus a family office long only banks analyst approaches his or her day, the data they're looking at, the decisions they make, what good management means, what a good bank is versus a good tech company. It's a very specific exercise. And so that cloning of your own process is, I think, a real bottleneck. [00:28:30] S1: Yeah, yeah, yeah. [00:28:32] S0: And I like your processes, Matt. We've done similar, but it still does take time off the desk to really start to do that. [00:28:42] S1: Yeah, for sure. I mean, think it's a similar story to having to spend the time to learn AI. You actually have to spend the time to build the materials that will give you this benefit with these models. Right. Yeah. I mean, you know, pulling yourself out of the weeds to do this is hard, right? Because everyone has a real job to do and it's not learning AI or building the tools to make the AI better later.
00:28:42 · Matt Stockton, Brett Caughran
[00:28:42] S1: Yeah, for sure. I mean, think it's a similar story to having to spend the time to learn AI. You actually have to spend the time to build the materials that will give you this benefit with these models. Right. Yeah. I mean, you know, pulling yourself out of the weeds to do this is hard, right? Because everyone has a real job to do and it's not learning AI or building the tools to make the AI better later. [00:29:13] S0: Yeah. One other bucket I've really been struggling with a little bit is, you know, with the open tools now, whether it's co work or codex or perplexity Computer, I can get to very good prototypes very quickly on pretty much every workflow of the investment process. I still struggle a little bit with consistency. I struggle a little bit with accuracy in those. And I struggle with the token economics of how that scales up to an investment process. So that sort of like last mile problem of productioning those demos still feels like a hairy issue. What have you seen? Like, are the sort of the bags in your tool, you know, the tools in your toolkit or what you've seen clients do to actually production these demos?