Episode

Give Users the Wheel

Podcast
Data Skeptic
Published
Jun 23, 2026
Duration seconds
2128
Processing state
not_requested
Canonical source
https://dataskeptic.com/blog/episodes/2026/give-users-the-wheel
Audio
https://pscrb.fm/rss/p/mgln.ai/e/35/traffic.libsyn.com/secure/dataskeptic/Fuyuan_Lyu_No_Ads_V1.mp3?dest-id=201630
JSON
/v1/public/podcasts/data-skeptic/episodes/give-users-the-wheel
Markdown
/podcast/data-skeptic/give-users-the-wheel.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/data-skeptic/episodes/give-users-the-wheel/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/data-skeptic/give-users-the-wheel.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

What if you could simply tell a recommendation system what you want instead of relying on likes, dislikes, and watch history? Kyle Polich talks with Fuyuan Lyu about the DPR framework, which combines large language models and traditional recommender systems to give users direct control over recommendations through natural language. Together they explore how conversational interfaces could transform platforms like YouTube, TikTok, and news feeds while preserving the strengths of modern recommendation algorithms.