Episode Details

Back to Episodes
Building a Podcast Graph That Doesn't Suck

Building a Podcast Graph That Doesn't Suck

Episode 6087 Published 1 week, 4 days ago
Description
A listener named Daniel wants to rebuild how we explore a podcast archive: not a feed, not a hairball graph visualization, but a sequence of small decisions — like a dating app that learns your type and walks you through the archive one connection at a time. We dig into why force-directed graph views are a "screensaver with a fan club," what Spotify's 2024 podcast graph actually did (and why listeners never saw it), and which open source players are still alive. Then the database question: can you run Neo4j next to serverless Postgres to copy fourteen rows a day? What we found involves logical replication slots, a Business Source License, and a cautionary tale about an embedded graph database that got acquired and archived overnight. Episode 6087 — myweirdprompts.com/n/6087 (permanent short link: myweirdprompts.com/842119)
Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us