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 →

Anant Bhardwaj no published score: only 1 usable exchange 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 ✕
1exchanges match
1on raw tape
0redirected or not addressed
Answered raw tape D 4 · C 4 · P 4 · Cm 4 4.00

Q So, I know that's going to be hard to respond in a few seconds, but what happens behind the scenes, right? I mean, this, this has to be some like data cleaning and formatting and all the things, right? If you build a universal sort of building block following applications, then you have to integrate with all sorts of disparate data sources. What, how does that, how does that work?

A So you have to provide the code building blocks. Like, if you think about, like, if you had to re-architecture, if you, if you were engineering architect of a company, and if you had to basically build this, what all building blocks would you need? Then you might need image processing building block that basically extracts all of those things. Then you might need basically ability to magically extract those things. That's an amazingly, amazingly hard problem. And we have something called program synthesis that basically allows you to do that. Um, and then you need an ability to run mathematical computation. How do you run mathematical, mathematical computation at scale? So it's pretty similar to lambda function, the way you saw, but it basically uses Excel-like grammar, and then from there it basically invokes. The reason why we had to build all of those ourselves is because, ah, we had to run on-prem, or we had to run everywhere. So we could not use any other cloud stuff, but that also allowed us to kind of like rethink everything from scratch, which means that now we could take this, compile this into a single binary, and you can run anywhere. Portability is one of the most important things, because that gives the distribution of stuff. Like, for example, if a company creates something for U.S. markets, now you can go in, in like seven days, now they can sell to every, every …

AI assessment note: “we have something called program synthesis that basically allows you to do that”

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.