Star Treatment

Does prominence change the questions? Every guest, plotted: their public prominence (rated 1–10 by an LLM, methodology below) against the host pushback they met, measured from every diarized word of their episodes.

An aggregate AI reading of public interviews: pushback per exchange, plotted against guest prominence. It describes questioning patterns across the whole catalogue, not any single guest, and every point opens to its episode. full disclaimer →

0.00pushback per +1 prominence
0.0/10host pushback, prominence 8–10
0.0/10host pushback, prominence 1–4
0guests measured
0 of 0 guests shown
0 2 4 6 8 10 12345678910 prominence → (1 to 10) host pushback /10

dot size = rated episodes · gold line = average per prominence level · every dot links to the person

All guests, by prominence

GuestProminenceHost pushbackGuest pushbackEps

host and guest pushback: scored 0-10 per topic segment by an LLM with a published rubric over the diarized transcript; an episode’s number is the peak-weighted p75 · prominence: rated 1–10 by an LLM from the person's public profile · full method on /methodology.

Made with StarZero

Turn any episode into a week of clips.

This entire site, over 100 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.