Straight Answers

“I should steer the car. So I don't, you probably want to remove that.”

answered: “We have a diversified bet strategy internally.”

“They're going on Google shopping and looking at the, the wall of items. How do you collaborate internally to figure out where AI goes?”

answered: “when I meant like shopping, I, I sort of tried to boil down”

“How do you pick? You got all these people reaching out, you know, they're just good and mad.”

answered: “first thing we need to like define some structure and work out”

“Um, or do you sort of glom them onto a single agent? I don't know if you have an opinion, obviously, because agent is very ill-defined, but I'll just put it out there.”

answered: “indexing by definition is a trade off. Like when you index data”

“But then I think from there, the actual exploration and making that great, that is a hard design task still. So how do we lower the floor for everyone coming in, but also raise the ceiling, make us the designers can do even more and produce even greater work?”

answered: “So I'm curious, like, if there's something that you think about”

“Say it was, what about all of Amazon data? Shopping data, right?”

answered: “If we were to look at purely social media... if I had to really pick, Facebook”

“Basically, that's really the key question here. So optimizing the embedding model, um, even changing the way you like chunk things, these all shift the embeddings.”

answered: “So the retrieval is interesting. I got a bunch of startup pitches that are like”

“And then how do you kind of prioritize, okay, this is worth going into more of the, and we'll talk about Pydantic AI and all of that. What was maybe your early experience with LLAMPS and when did you figure out, okay, this is like something we should like take seriously and focus more resources on it?”

answered: “I'll answer that, but I'll answer, which I think is like a kind of parallel question”

“Any fun Korean celebrity stories? Cause you work with so many influencers.”

answered: “We have a bunch baking right now, but I think it was... something more generally”

“Like what percentage genre do you put? Like also do you split vocals and instrumentals?”

answered: “without divulging too much secret sauce, um, it's a, it's at least similar”

“Uh, what's up on mind for you in terms of building a team? Who should, who are you calling for?”

answered: “to stay on the tiny box for, for, for, for one minute.”

“You would assume, like, very simple for human to think about, but if the model is saying you should walk to the car wash, you know. Any, anything here?”

answered: “It's less, uh, what can we solve? But I think it's more about”

“You only have 35 people, so I'm sure they're not all spending 10 K a month. What's kind of the distribution?”

answered: “we have some, you know, power users kind of all the, all the way down”

“Does GitHub go away? And like, what, what is the AI out of read-read?”

answered: “A lot of agents you'll build on Dreamer Do things in the background.”

“Um, why Netherlands by the way? Or is it, is that because of Chrome?”

answered: “we had a data center in there. Um, so, I mean, I think this gets”

“Why you could have done it in an extension? Like, can you maybe just explain more of those limitations?”

answered: “limitations around, like, APIs are pretty well documented. I don't know if we need”

“And then when did you go, like, full-time on Snips?”

answered: “how that started was the friend of mine who got me into machine learning”

“Do you see people, uh, using the files and the search API together where you can kind of search and then store everything in the file so the next time I'm not paying for the search again and like, yeah, how should people balance that?”

answered: “Let me first tell you about how I've seen a really cool way”

“Before we move to the next layer of abstraction, anything else on MCP you mentioned?”

answered: “Let's move back and then I'll tie it back to MCPs.”

“And then took seven years to actually get them on the street. Can you share about maybe like the last one percent that was really hard to, to get done technically?”

answered: “There's a concept called, uh, prize policy, which is so that there's, there's different ways”

“I mean, it underlines it if you reach a 150 tokens or a 150,000 tokens or something. How do you teach this to the user?”

answered: “we're in the church of context engineering at the Chrome office.”

“Is this like closer to ragged into like a XR, like a public search thing? Like how do you segment like the different types of search?”

answered: “if you want to build a really big database company, sort of, you need”

“You know, how, how do you think about what people should do with it today? And maybe like the vision that you have for it overall, it's like the impact that it should have on people's work and life that is not working.”

answered: “I get asked quite frequently about how I use AI”

“I think the, the, the typical challenge for people is understanding, like, that has value, uh, and then, like, there are other people who are also offering open source models, right? Like, your moat is, is your ability to offer, like, a good experience for all these customers, but if your existence is entirely reliant on people releasing nice open source models, other people can also do the same t”

answered: “we look at our, the value prop from the lens of application developers”

“Um, like, uh, is there, is there, like, what's the interest there? Um, you know, is it all of a kind, ultimately, in your, in your mind?”

answered: “we're gonna talk more about that in a second, but a hot take here is”

“Yeah, excellent. Um, by the way, I like to quantify things when you say make things over, like, uh, is there a target range of, like, MFU that you typically talk about?”

answered: “in training, everyone just talks about MFU, right? But then on inference”

“Obviously, you're working on one. Um, what are some of the other branches of the tree that people should go under?”

answered: “I don't think I'm working on one of the six insights.”

“So what were your results? What's interesting?”

answered: “the kind of way that we measure Performance here is that”

“But yeah, well, what did you think of the Dario memo? Were you, like, surprised?”

answered: “I don't have a take on that. I think more broadly, uh, you know”

“This is clearly a market clearing problem. What's the market solution here?”

answered: “one of the reasons I joined Stripe and one of the things I have loved”

“Um, it's a pretty simple concept. Like what's the source of error?”

answered: “I've been talking to Harrison actually about like a more like structured way”