Aravind Srinivas: preference

Transcript context

…That’s an engineering challenge, but when it’s done right, obsessively reducing latency, you actually have, there’s a face shift in the user experience where you’re like, holy, this becomes addicting and the amount of times you’re frustrated goes quickly to zero. And every detail matters like, on the search bar, you could make the user go to the search bar and click to start typing a query or you could already have the cursor ready and so that they can just start typing. Every minute detail matters and auto scroll to the bottom of the answer instead of forcing them to scroll. Or like in the mobile app when you’re clicking, when you’re touching the search bar, the speed at which the keypad appears, we focus on all these details, we track all these latencies and that’s a discipline that came to us because we really admired Google. And the final philosophy I take from Larry, I want to highlight here is, there’s this philosophy called the user is never wrong. It’s a very powerful profound thing. It’s very simple but profound if you truly believe in it. You can blame the user for not prompt engineering, right. My mom is not very good at English, so use uses Perplexity and she just comes and tells me the answer is not relevant and I look at her query and I’m like, first instinct is like, “Come on, you didn’t type a proper sentence here.” She’s like, then I realized, okay, is it her fault? The product should understand her intent despite that, and this is a story that Larry says where they just tried to sell Google to Excite and they did a demo to the Excite CEO where they would fire Excite and Google together and type in the same query like university. And then in Google you would rank Stanford, Michigan and stuff, Excite would just have random arbitrary universities. And the Excite CEO would look at it and was like, “That’s because if you typed in this query, it would’ve worked on Excite too.” But that’s a simple philosophy thing. You just flip that and say, “Whatever the user types, you always supposed to give high quality answers.” Then you build a product for that. You do all the magic behind the scenes so that even if the user was lazy, even if there were typos, even if the speech transcription was wrong, they still got the answer and they love the product. And that forces you to do a lot of things that are currently focused on the user. And also this is where I believe the whole prompt engineering, trying to be a good prompt engineer is not going to be a long-term thing. I think you want to make products work where a user doesn’t even ask for something, but you know that they want it and you give it to them without them even asking for it. One of the things that Perplexity is clearly really good at is figuring out what I meant from a poorly constructed query.…

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