Zero-Shot Learning
00:20:21 · Adarsh Hiremath
[00:20:21] S2: I mean, the key thing is just citing the relevant company context. Right? If the agent is saying a fact and it is unable to cite the company context, it should automatically stop. Right? That's a functionality we already have in the Right. Merkur platform. That's just like maybe level one. Level two is if it's able to cite the context but gets the wrong interpretation, you need to either have a human review the trajectory to create the eval or have an LLM review the trajectory. Because some LLMs might be, unable to get the right answer, right, or even able to get the right answer. But they might even be better at reviewing the trajectory. Right? So it's like you could arrive at the wrong answer, but it could know that it arrived at the wrong answer and why, and it could also arrive at the right answer and know that the reasoning was wrong and why. So you typically wanna have multiple levels of review on the actual trajectory of the agent.
00:21:06 · Dev Tagare
[00:21:06] S1: Yeah. Super cool. And in your observation, lot of these incorrect answers or hallucinations usually tend to happen in what you would describe as conversational agents. I'm asking a question, I'm getting an answer back quickly in the pursuit of quick answers, often grounding is ignored sometimes, citations are ignored sometimes, the models underthinking, overthinking, what have you. Are you building towards a world where quality or precision takes over conversational kind of experiences? And there's a curve there. Right? Like, you trade latency for accuracy, so to say, but then eventually you wanna bring accuracy to latency.
00:21:51 · Adarsh Hiremath, Nancy Wang
[00:21:51] S2: Right. Uh-huh. Yeah. So so addressing that, that's one of the reasons I'm most interested in in evals as the foundational infrastructure investment that makes all of this possible, which is it allows you to select the best model for a specific use case. There is no quantitative way or data driven way to make that selection unless you have an eval suite that is representative of the job to be done and is comprehensive across the task and the trajectory and the output. That's why we're so so so excited about evals and what they mean for the future, because the models are getting to the point where the real bottleneck is applying evals throughout all the economically valuable parts of the economy and then... And steering the models in in the right way. To your point about conversational interfaces, versus maybe using a agent as the backbone of, like, a broader system. I would say that in conversational interfaces where the person is working directly with the agent Mhmm. Mistakes are are actually a little bit more pronounced and easy to to to see. Right? It's like the agent said something that doesn't quite make sense or just weird. Right? There... There's that. But I actually think the more dangerous failures are the ones happening behind, the scenes of these broader systems where you don't have a conversational interface to diagnose the failure. And often these failures happen silently, and often they have much, much larger consequences than one would anticipate or want. [00:23:07] S3: Right.
00:23:07 · Nancy Wang, Adarsh Hiremath
[00:23:07] S3: Right. [00:23:08] S2: Again, the way to correct for that is an eval investment that is representative of the task that that agent is doing. [00:23:13] S3: And so that actually brings us to, I think, a fundamental question that, especially as a security company, we think about a lot, which is trust and the ability to handle edge cases. Because oftentimes, let's say in security, the difference between a false positive and a false negative is potentially your company ads have been headlines. So, the question there is, how do you think about last mile coverage? Do you go for more, let's say, you know, broad set, or do you wanna go for confidence on a very narrow slice of the problem? [00:23:41] S2: I typically say broader. The good part is that the models have reached a level of intelligence where they, if they have all the right scaffolding, can generalize. But you won't know unless you have like a broad sample of the problem, and you put that in an eval set. On the topic of 1Password and trust and safety, one of the problem spaces that I'm also really excited by is just authentication for agents. Right? Mhmm. Humans need this to Yep. To to make sure their activities are secure. Agents need this as well. I think there's a very strong case to be made that the addressable market of agents taking actions that need to be gated in the appropriate way is gonna be larger than humans in the next couple years, if it isn't already. So I'm I'm very, very excited about that, and what that means for 1Password and other companies focusing on security.
00:23:41 · Adarsh Hiremath, Dev Tagare, Nancy Wang
[00:23:41] S2: I typically say broader. The good part is that the models have reached a level of intelligence where they, if they have all the right scaffolding, can generalize. But you won't know unless you have like a broad sample of the problem, and you put that in an eval set. On the topic of 1Password and trust and safety, one of the problem spaces that I'm also really excited by is just authentication for agents. Right? Mhmm. Humans need this to Yep. To to make sure their activities are secure. Agents need this as well. I think there's a very strong case to be made that the addressable market of agents taking actions that need to be gated in the appropriate way is gonna be larger than humans in the next couple years, if it isn't already. So I'm I'm very, very excited about that, and what that means for 1Password and other companies focusing on security. [00:24:21] S1: That's basically definitely blooming. [00:24:23] S3: I would say, appreciate the call out. I mean, especially with agent swarms, I mean, you're already applying a multiplier effect on the human to agent ratio, and especially agents doing, you know, real work out there and taking real decisions. [00:24:34] S1: Even, like, out in delegation, right, like, you're talking to a third party SaaS from, like, any one p, need a mechanism and you need coordination across. So, yeah, that that space is definitely booming a lot. Related question to this, slightly different from the security space, Adarsh, the context of an enterprise evolves over time. [00:24:52] S3: Mhmm.
00:24:52 · Nancy Wang, Dev Tagare
[00:24:52] S3: Mhmm. [00:24:53] S1: Right? Like, today, I may be doing... Let's let's consider I'm a food delivery app. Tomorrow, I could do groceries. Day after, I could do something else. You know, in the future, I could do drone delivery, something like that. Right? So the context for an enterprise evolves. How do you keep this context evolution in perspective as you develop? And a related question to that is, in a more simpler way, how do you solve for data drift?