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 →

Daniel Evans no published score: no 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
0on raw tape
0redirected or not addressed
Answered produced feed D 5 · C 5 · P 4 · Cm 4 4.60

Q Interesting. What, why is that? I mean, I'm, this isn't a right or wrong answer. I'm just curious.

A Yeah, yeah, yeah. It's, it's solid tech, right? They spent two years on the tech. The AI is pretty robust and being able to do this in real time is, is very, very difficult because you've got to balance the machine vision, uh, machine learning components with speed, right? Cause you only have so many resources on a, on a machine. Uh, so I think that is the hard part and they spent a good two years dealing with different elevations of Cameras and different viewports and different angles, right? So being able to accommodate all of that into machine vision algorithms is, is a lot of heavy lifting. Uh, and I think that is, is done now. And so now we're getting very nuanced into, you know, snaps and runs versus pass and things like that. So we're getting into some really interesting stuff now.

AI assessment note: “being able to do this in real time is, is very, very difficult”

Answered produced feed D 4 · C 5 · P 4 · Cm 4 4.30

Q Yeah, fair. Okay, take me back here. When did you write the first line of code for this?

A So I was not one of the original founders of this. I actually came in because a friend of mine, uh, you know, they were kind of struggling a bit, uh, after a couple of years of development. And, uh, he asked me to kind of come in and stabilize things and, and set things up for the future. But the original intent was, uh, the founders were, were big fantasy players. There was three of them. And, uh, one of the founders really wanted to be able to get the Alvin Kamara touchdown in his, in his feed, like as soon as he got it so that he could essentially send it out to his friends and rub it in. Uh, and that was kind of how it was born. Uh, they started to kind of cut games themselves manually, uh, and then said, you know, this is crazy. Uh, so they went digging into the academic sphere and found somebody that had written a book on using machine vision and machine learning to do this and hired him, bought his work, and the rest is history.

AI assessment note: “So I was not one of the original founders of this.”

page 1
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 2,600 episodes 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.