Invest Like the Best with Patrick O'Shaughnessy
00:55:37 · Patrick O'Shaughnessy, S0
[00:55:37] S1: the best product experience. [00:55:39] S0: Your finance team isn't losing money on big mistakes. It's leaking through a thousand tiny decisions nobody's watching. Ramp puts guardrails on spending before it happens. Real time limits, automatic rules, zero firefighting. Try it at ramp.com/invest. As your business grows, Vanta scales with you, automating compliance and giving you a single source of truth for security and risk. Learn more at vanta.com/invest. Bridgeline offers one unified platform that automates away the complexity across portfolio accounting, reconciliation, reporting, trading, compliance, and more, all at scale. Schedule a demo at ridgeline.ai. Every investment firm is unique, and generic AI chatbots don't understand your process. Rogo is built by finance professionals. It's connected to your data, learns your process, and quickly produces client ready outputs. Check them out at rogo.com/invest. The best AI and software companies from Open to cursor to perplexity use WorkOS to become enterprise ready overnight, not in months. Visit workos.com to skip the unglamorous infrastructure work and focus on your product. [00:56:48] S1: What have been the blunders so far? Like, what's gone wrong? What have you done about it? This is just gonna be an explosion of emergent properties and mistakes, and the end's gonna be really high. How do you think about things to guard against proactively, things to be reactive against? Like, talk us through the darker side of building this or the harder side of building this.
00:56:48 · Patrick O'Shaughnessy, Noah Shinn
[00:56:48] S1: What have been the blunders so far? Like, what's gone wrong? What have you done about it? This is just gonna be an explosion of emergent properties and mistakes, and the end's gonna be really high. How do you think about things to guard against proactively, things to be reactive against? Like, talk us through the darker side of building this or the harder side of building this. [00:57:06] S2: I think it's important to never be reactive and to always be proactive to look ahead for what new surface areas are being introduced and what new risks might come. And I would say this is the reason why we ran this early access invite program from the start, which was, yes, an early version of the product didn't have firewalls in place. It didn't have these active monitors in place and so many other pieces of infrastructure that were meant to get ahead and be proactive about being able to provide that much control to the agent and the existing system to be able to secure. So, yes, there's an early version of the product that had some of these qualities or some of these mistakes, and we addressed it. We went above and beyond and didn't just patch the problem. We built a different system to systematically solve these types of problems. So I think the key here is, again, I said this earlier, the user should always be in control of their data. The user can share as much as they like or as little as they like. And if they ever change their mind at any point in time, they can always retract to access to these certain services.
00:58:02 · Patrick O'Shaughnessy
[00:58:02] S1: Makes me wonder what's the future of security? Even if you're the best in the world at this, which maybe you'll have to become, you're gonna have so much information and context on so many people. And security is a big problem, I think, across the world. I mean, all these great hacking examples that we've studied now, it's wild what these things can do. The capabilities are gonna get stronger and so on. I'm just curious for you to riff on the future of security and safety and early in technology revolutions of the past. Always, there's these enormous hacks. There's enormous data breaches and so on. It's hard to imagine this won't happen in this technology revolution too. How do you think about this and the responsibility of providing safety, given how much you'll know about people?
00:58:39 · Noah Shinn, Patrick O'Shaughnessy
[00:58:39] S2: It's the most important problem. I think it comes to building security and safety and a mindset towards some of the core values of the company and the people and the way that you build product. This is topical because anytime in the past twenty, thirty years when any new breakout or new consumer experience has been revealed, there's always been immediate backlash of, woah. This is different... Confusing different with being unsafe and seeing some of that now. But, also, I think staying core to the principles that you hold. The user's always in control of their data. They should never feel out of control. Being proactive about the systems that you put in place to be able to get ahead of these types of things. If I call out one example, a hallucination case that existed, language models hallucinate all the time, but with a product like this, you don't want a language model to be hallucinating. So we put in place a more systematic solution that will detect before an action is taken, before a thinking trace is executed as a tool call, it is validated and scrutinized by something that is decoupled from the same incentive system as the underlying agent. [00:59:39] S1: It's like a watchdog. Yeah.
00:59:39 · Patrick O'Shaughnessy, Noah Shinn
[00:59:39] S1: It's like a watchdog. Yeah. [00:59:41] S2: A filter that's able to find this proper noun was just generated out of thin air due to some sampling error in the underlying model. It's very easy in hindsight to be able to capture these types of mistakes. And these are hardened. So we have world class security teams that are constantly working proactively to find harder and harder adversarial cases to try to find edge cases here and there, and it's becoming rarer and rarer over time. One subtle part about building a platform like this is that it's getting better over time. As we continue to do more adversarial testing, as we continue to be more creative about certain edge cases, these models are just getting better and better over time towards being robust to these types of attacks. [01:00:19] S1: On the other side of the ledger, everyone always shows that beautiful visual of each generation of the iPhone, and you can see it getting better over time and more and more refined. What's that arc for you? It's so interesting because it's not an application. It's not a device. It's an interaction through existing communication channels, WhatsApp and iMessage, etcetera. What are the things that you're adding and envision adding over time that will make the platform and the product more powerful than it is today?
01:00:43 · Noah Shinn
[01:00:43] S2: The product experience right now is very simple. Simplicity is one key that we focus on. But I actually think that it becomes even more simple over time. We may roll out an application in the near future, but I actually think that we're going to trend more towards a simpler interface, which is, do you even need to open the iMessage application and type in a certain piece of content and send the message out and then look at what the response is after when it's done? There's a certain subset of users that interact with Instinct only through voice, actually. Like, more than 90% of the interaction of the messages that they send to Instinct are primarily through voice. I even have this action button, the action button Yeah. Yeah. On on your phone. I can click on the action button and say, like, say hi to Patrick in in two hours from now. I think you have his email address. You can go send him an email. And I don't even now need to unlock my phone and open the iMessage application and type the message in. You can even imagine with real time voice with voice recognition that knows what your voice sounds like and has the discretion to know when you're addressing it and not addressing it, where you could have, let's say, like an AirPod and not a new type of AirPod, just like an AirPod because it's good enough, And it's just on. And it's just on, and you might be going on a hike or on a bike ride or on a walk, on a run, or something like that. And you're just catching up, like, hey. This contract need to review. Okay. I I need to review that. Or this news article just came in, and here's the headline, and here's the takeaway. This new project was released, and you should take a look at this. And you're just like... And you're you're like, okay. Got it. Got it. Put that on my calendar. That's fifteen minutes. Okay. Yeah. That's not important, so go clear that part out. This person needs my help. I know the answer to that, so just tell them that it's this. It's going to be much, much easier over time. I think that there are long term and short term considerations here, where I think in the long term, the interface has become much simpler. But in the short and medium term, maybe there are more expressive interfaces to be able to share.