Speaker unverified: belief

Transcript context

…It’s hard to find, hard to control, there’s not a momentum, there’s… And the intention should be clear, when I start moving towards a scroll bar, there should be a snapping to the scroll bar action, but of course… Maybe I’m okay paying that cost, but there’s hundreds of millions of people paying that cost non-stop, but anyway. But in this case, this is necessary, because there’s an extra cost paid by Noland for the jitteriness, so you have to switch between the scrolling and the reading. There has to be a face shift between the two, like when you’re scrolling, you’re scrolling. Right, right. So that is one drawback of the current approach. Maybe one other just sort of case study here. So, again, UX is how it works, and we think about that holistically, from the… Even the feature detection level of what we detect in the brain, to how we design the decoder, what we choose to decode, to then how it works once it’s being used by the user. So another good example in that sort of how it works once they’re actually using the decoder, the output that’s displayed on the screen is not just what the decoder says, it’s also a function of what’s going on on the screen. So we can understand, for example, that when you’re trying to close a tab, that very small, stupid little X that’s extremely tiny, which is hard to get precisely hit, if you’re dealing with a noisy output of the decoder, we can understand that that is a small little X you might be trying to hit, and actually make it a bigger target for you. Similar to how when you’re typing on your phone, if you are used to the iOS keyboard for example, it actually adapts to target size of individual keys based on an underlying language model. So it’ll actually understand if I’m typing, “Hey, I’m going to see L.” It’ll make the E key bigger because it knows Lex is the person I’m going to go see. And so that kind of predictiveness can make the experience much more smooth, even without improvements to the underlying decoder or feature detection part of the stack. So we do that with a feature called magnetic targets, we actually index the screen, and we understand, “Okay, these are the places that are very small targets that might be difficult to hit. Here’s the kind of cursor dynamics around that location that might be indicative of the user trying to select it. Let’s make it easier. Let’s blow up the size of it in a way that makes it easier for the user to sort of snap onto that target.” So all these little details, they matter a lot in helping the user be independent in their day-to-day living. So how much of the work on the decoder is generalizable to P2, P3, P4, P5 PM? How do you improve the decoder in a way that’s generalizable?…

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