Shawn Wang: belief

Transcript context

…So like whenever I see something that blows my mind, the way that that initial hugging face demo did, that was like the start of everything. I'll start from the beginning. If I don't know anything, I'll start by just trying to get a mental model of what is happening. Like first I need to understand what, so I can understand like the why, the how and the why. And once I can understand that, then I can make my own hypotheses about like, okay, here are the assumptions that the authors of this made. I mean, here's why maybe they're correct. Maybe they're wrong. And here's how like I can improve on it and iterate on it. And I guess that's the mindset that I approach it from is like, once I understand something, like how can it be better? How can it be faster? How can it be like more accurate? And so I guess for anyone starting now, like I would have used find if I was starting now. Cause like I would have loved to just have been able to say like, Hey, like I have no idea what I'm doing. Can you just like be this like technical research assistant and kind of hold my hand and like ask me clarifying questions and like help me like formalize my assumptions like along the way. I would have loved that. But yeah, I just kind of did that myself. Recording Looms of yourself using Phind actually would be pretty interesting. Yeah. Because I think you, you would use find differently than people would by themselves. I think so. Yeah. I generally use Phind for everything, which is definitely, yeah, it's like, no, no, even like non-technical questions as well. Cause that's just something I'm curious about, but that's less of a usage pattern nowadays. Like most people generally for the most part do technical questions on find. And that is completely understandable because of very deliberate decisions that we've made in how we've optimized the product. Like we've optimized the product very much in a quality first manner as opposed to a like speed first or like some balance of the two matters. So we're like, we have to run GPT-4 or some GPT-4 equivalent by default. And like, and it has to give like a good answer to like a very demanding technical audience where people will leave. So that's just the trade off. So like sometimes it's, it's slower for like simple questions, but like we did that on purpose.…

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