The Exchanges

Every argument clarity score on this site is built from rows on this page. Each question and answer was assessed with names hidden, the host's own answers included, on four things from 1 to 5: directness (does it answer the question asked), coherence (do the ideas follow), precision (concrete details and clear references), compression (says a lot per word). The weighted mix (30/30/25/15) is the exchange score. A person's published score averages their exchange scores on raw tape only, at least 8 of them, shrunk toward the cohort mean. Full method →

Matthias Niessner no published score: only 2 usable exchanges on raw tape, and a fair score needs 8+ record → ← everyone

Every exchange below was scored with names hidden, four dimensions each from 1 to 5. An exchange's score is 0.30·directness + 0.30·coherence + 0.25·precision + 0.15·compression. The published score averages the raw tape exchange scores and shrinks small samples toward the cohort mean, so five great answers can't beat twenty good ones. Produced feed rows count only toward coarse estimates, never toward a full score.

clear all ✕
2exchanges match
2on raw tape
0redirected or not addressed
Answered raw tape D 5 · C 5 · P 4 · Cm 4 4.60

Q on real-life actors, uh, but you have the ability through AI to make them say, um, things, uh, in, in a bunch of different languages with, uh, expression and, and, and all the things. So this is at the intersection of voice and computer vision and all the things. Maybe walk us from a, an AI perspective. Um, how, how does that work? Like, what, what is this based on?

A Yeah, so a lot of the origins of this research actually comes from computer graphics from the movie industry, so when you're having like a, you know, an actor that is, has a stunt double or something like this, you have to virtually replace, edit the faces, edit the actors, and the movie industry has been, you know, over the decades, has made successive progress in order to make it easier, um, for editors, for artists, um, to, to mitigate the effort there, and Kind of the thing that happened in the last, in years, let's say in the last, well, 10 years, like a lot of things in AI and deep learning have happened. So traditional graphics methods have been augmented with AI methods now, and this has become a lot easier. So you have now generated by methods like generating serial networks and these kinds of technologies, they help a lot to make this process even easier than it used to be before. So instead of having artists and so on, but manually fix like face replacements of, of actors or so, you now have an AI that does it all automatically.

AI assessment note: “traditional graphics methods have been augmented with AI methods now”

Answered raw tape D 5 · C 5 · P 4 · Cm 4 4.60

Q Great. Do you want to remind, uh, folks, uh, what, uh, the generative and virtual network is?

A Yeah. So the idea of a generative network is, um, you, you show a network, instance, a bunch of images of faces and the network kind of learns how to, to, to create new images from faces, the kind of learning the distribution of existing people that the neural network has seen, and then you kind of can create new images that look like faces, but they're not specifically any of the existing observed images. And so there have been a lot of works around GANs in the, in the computer vision AI history, um, in the last, well, five, six, seven years. Um, and, and now there's a lot of new stuff coming that you can actually make not just images out of it, but you can actually create full videos out of it and can make these things look very, very realistic. You can create very high resolution videos and make them pretty much indistinguishable from any real videos.

AI assessment note: “So the idea of a generative network is, um, you, you show a network”

page 1
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.