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 →

Amanda Stent 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 No, I think it's remarkable. For disclosure, I worked here for four years, um, and was really quite impressed. Um, anyway, how does the, the handoff work between the, the machine and the humans? You mentioned the human in the loop. How does that work practically?

A Yeah, so when you have every one of our machine learning based applications has a different trade-off between precision, recall, and speed. Um, and it's really not optimize F all the time or optimize latency all the time. It's a different, it's a different trade-off for each one. When we have time or offline if, if necessary due to latency constraints, we use an assortment of active learning methods. Active learning? Active learning methods. Um, and we have a team of data scientists Some of them with very specialized expertise in finance, and some of them with more generic expertise who help us to label data, who help us to design the algorithms, who provide subject matter expertise, um, so that we can continually improve all of our systems. And that's something that historically has been done mostly with rule-based systems, but today we do it with, um, deep learning and a lot of decision trees.

AI assessment note: “help us to label data, who help us to design the algorithms”

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.