Speaker unverified: prediction

Transcript context

…Yeah, so I mean, to me, you've said the magic words. Like I've been a big advocate kind of since we started the company and even since I was at Meta that like an ounce of prevention is worth a pound of cure. Like being there before something happens or as you pointed out, maybe you can optimistically let a message through and then retract it quickly is just a better approach than finding stuff three to seven days later and saying, oh, we screwed up, we need to block or ban this user. And in the case of AI, what would you even do three to seven days later other than maybe like, I don't know, add it as a training example for the next fine tune or something like that? As far as the architecture goes, so we have a couple techniques that we're using. So one, yes, we do use some very small models that are already pretty fast. It also turns out that breaking a policy down in the way we do into atomized bytes gives us some unique advantages on sort of the latency front. The questions we're asking are all pretty small. They tend to share a prefix, basically. And so we're able to sort of benefit from quite a large amount of prefix caching. We also, generally speaking, at least first pass, we're not generating much. There's really no decode step for us. What we, I mean, I'm happy to share some of the architectural details. Like we essentially are training a binary classification head onto an LLM, right? We don't initially anyway need some, we don't need the questions answered with an actual yes or no. And in fact, it's counter to our objectives. to do so, we actually want to know what is the probability that the answer to this question is yes, basically. And that I don't want to get, I don't want to, I have a tendency to sometimes go on tangents. So I'm going to try to contain myself here and maybe we can come back to like the benefits of having those probabilities and the abstained gap and all that. There's another common thing in moderation safety guardrails control, whatever you want to call it, which is that for most, for the majority of policies, upwards of 90% of all the content you're ever going to see is fine. Like it's a real needle in a haystack problem, right? Like you're looking for a small sliver. The only problem is that very often that sliver has high severity, has real risk associated with it. And so we have a number of layers sort of in front, you mentioned lightweight classifiers. They're not simple binary classifiers, but we do have a number of much lighter weight models that sit in front of our, I guess what I would call like our main QA engine that can give us with reasonable confidence and high recall, that's the important part, a quick answer up front. And so the idea is like, For, let's say, just for argument's sake, let's say 90% of what we're gonna get sent from a particular customer is fine. Really, there's no problem. We don't need to look at it for real, basically. e, For, let's say, just for argument's sake, let's say 90% of what we're gonna get sent from a particular customer is fine. Really, there's no problem. We don't need to look at it for real, basically. Ideally, we wanna try to take, let's say, half of that and filter it out right away and just approve it, basically. And if we can do that, then on average, the latency that we're offering the customer, I mean, for those cases, we're gonna be sub 200 milliseconds, basically. And then because our models are pretty damn fast, like for the rest of the cases, we're sort of in the three to 500 millisecond range when we actually have to do a deeper scan. I will say it also varies a lot by modality and there are aspects there that are just hard to get around. Like text is very, very fast. Those sort of the numbers I just quoted. images are a little bit slower or we have to run a vision encoder. Like there's more steps. We have to very often resize the image. We have to potentially transform the format of it before we process it. So there's just built-in latency video, even more latency because we first have to sort of pull the video from wherever it is. It could be very large, you know, et cetera. Rip out the audio, transcribe it. Like there's all these extra steps that we have to deal with. And to answer sort of that last question, like what is the What is the use case tolerance? I do think it depends a lot on use case. For some of our, for example, AI image Gen. customers, right? It's already taking 6 to 10 seconds to generate an image. So, you know, adding maybe 10% latency on top of that, because it takes us 1500 milliseconds to render a verdict, like it's not that big a deal. You know, it's not ideal maybe, but it's not noticeable to the user. And in my view, actually, that's what a lot of the tolerance is going to come down to. Like, how does it affect the user experience? Is it noticeable to the user? I just wrote this whole active guardrails piece kind of about this. It's where sort of our future focus is, on essentially being able to do what we do and do it on streaming tokens effectively so that we can kind of just be like the old days of TV and kind of just like run the conversation on a five second delay and bleep out anything that's bad basically. Because I just, what we see is that if we're asking too much from our customers of asking something of our customers that is going to significantly impact the user experience, then they are less likely to adopt the controls that they ultimately need. That's my feeling on it. Which raises the question a Spanish team has been answering all year. What comes after agents? But it's striking to me that you said you don't even have workflows as kind of a mental model. That seems to be at odds, at least with this anthropic launch. So would you critique their launch? You think something's off about that mental model? Should I go like revert my upgrade skill migration to the workflows paradigm? Where do you really disagree with that direction?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.