00:14:13 · Ruby Justice Thelot, Ben Hylak
[00:14:13] S1: Than earlier models? [00:14:14] S0: Well, even even just, like, smaller models. Like, I think they're just, like, really RLHF to have us very specific tone, to have, like, very well calibrated refusals, like, all of these sorts of things, which which is genuinely useful. Like, if you're making a personal agent or something, it's like... It just like, you know, if someone else tries even connecting to that... Like, it it just like... It just has a pretty good intuition on what to refuse Yeah. Kind of broadly. So it can be useful from like a security standpoint. But, like, yeah, they... Their tone is just... And their writing quality is, like, bad. Even, like, Kimi, you know, two point five was, like, actually, like, a pretty good writing model. [00:14:49] S1: Yeah. I think that they're optimized to deal with, like, code. [00:14:53] S0: Yeah. Of [00:14:54] S1: course. Like, you know, they're not optimized for, like, human interaction anymore. But, anyway, speaking of human interaction, you came from Apple's design team. [00:15:02] S0: Yes. [00:15:03] S1: So that's that's an interesting... And then you also did avionics [00:15:05] S0: at SpaceX? [00:15:06] S1: Yes. So that's an interesting trajectory to now, you know, working on, like, problems with agents. So how... What was, like, what was the trajectory? How did this happen?
00:15:06 · Ruby Justice Thelot, Ben Hylak
[00:15:06] S1: Yes. So that's an interesting trajectory to now, you know, working on, like, problems with agents. So how... What was, like, what was the trajectory? How did this happen? [00:15:17] S0: Yeah. So I... I've kind of had a... Yeah. I've had a weird trajectory. So, yeah, I went to school for robotics, and I was doing that sort of... Doing engineering. Really, really obsessed with avionics. Then I was really obsessed with, like, human computer interaction, but with robots. Yeah. It was like robot human interaction. And and I think I I got really, really interested in, like, AR at some point. Yeah. And that's that's why I was... [00:15:38] S1: This also happened to me.
00:15:38 · Ruby Justice Thelot, Ben Hylak
[00:15:38] S1: This also happened to me. [00:15:39] S0: Yeah. Exactly. Like, I... Because it was kind of like all the things I loved about, like, human robot interaction, but without the hard parts, like, literally the hard parts. Like, was like, you don't have to worry about how does, you know, how do robots walk upstairs or something. Just like, And you so, I think that unifying theme throughout my whole life is I love what I kind of call unbounded interfaces, where there's no really huge input space and really huge output space, or infinite. If you think about AR or robots or rockets are certainly unbounded, it's like, they're just like... There's all these things, like, AR can use your entire, you know, field of view. It can use Yeah. You know, and it can come close to you. It can come far to you. And and I was obsessed with solving that. So... Yeah. I was so I was a designer at Apple for, yeah, like, almost four years working on VisionOS. [00:16:28] S1: Yeah. Yeah. That... That's awesome. So what is, in your view, like, the mission of Raindrop? Do you... Where do you see it, like, possibly evolving after, like, simulations?
00:16:28 · Ruby Justice Thelot, Ben Hylak
[00:16:28] S1: Yeah. Yeah. That... That's awesome. So what is, in your view, like, the mission of Raindrop? Do you... Where do you see it, like, possibly evolving after, like, simulations? [00:16:39] S0: Yeah. So our mission is to protect the world from agent failures in both big ones and small ones. And so I think both parts are important. And I think it's actually been really humbling over the last few months seeing both as agents get deployed into more critical sectors, but also as our kind of customers have grown larger and larger, the issues we detect suddenly, you know, actually start to touch, like, human lives in really meaningful ways, like, where people's safety are concerned, etcetera. Mhmm. And, that's actually been we... We've, as a company, seen, you know, what we do change, like, a lot and and just the importance of it change. So it's been pretty cool. [00:17:17] S1: Yeah. And how do you think about building for, like, personal use cases versus for companies? [00:17:24] S0: You mean, like, individual developers? [00:17:26] S1: Yeah. Like, individual develop... I guess, yeah, I guess that... I'm speaking from a very SF, like, point of view where everyone is, like, a quasi developer.
00:17:26 · Ruby Justice Thelot, Ben Hylak
[00:17:26] S1: Yeah. Like, individual develop... I guess, yeah, I guess that... I'm speaking from a very SF, like, point of view where everyone is, like, a quasi developer. [00:17:32] S0: Yeah. Yeah. But but, yeah, I guess, like, for individual people versus teams, that sort of thing. Yeah. I think both are really, really important. Right? Like, I think you want to have a product that just, like, any random developer can sign up for or get value out of. At the same time, especially when when we started, a lot of the pitch was, you know... Like, we were working with companies that have, you know, millions of, you know, like, messages or events a day, and it's like making sense of that is insanely hard. So that was our focus at first. Yeah. I think simulations is our first step towards, you know, something that's useful even with like n equals one, where it's like... And I use it for things that I'm building. Yeah. And so it's like, just being able to say like, okay, I'm gonna merge, you know, I don't like the tone of this, or like, I don't like when it asks, you know, proposes a calendar event at this point in time. Let's try changing the prompt. Let's see if it actually fixes it. So that's been a really powerful flow for me. [00:18:26] S1: Yeah. That was gonna be my next question. Like, how have you personally seen, you know, efficiency improvement, process improvements from using simulations?
00:18:26 · Ruby Justice Thelot, Ben Hylak
[00:18:26] S1: Yeah. That was gonna be my next question. Like, how have you personally seen, you know, efficiency improvement, process improvements from using simulations? [00:18:34] S0: Well, yeah. We we use it a ton. I mean, Raindrop broadly, especially, like, we use a ton within Raindrop, which is kinda funny. Like, we have lot of agents actually. Everything is now [00:18:42] S1: so, like, recursive.