3 chapters across the catalog
The new follower data will help normalize popularity rankings across different platforms, preventing bias toward specific app demographics like Mac-centric Overcast users. Currently, the "popularity" column in the Podcast Index is based on internal heuristics and API traffic, which are prone to gaming. Integrating real subscriber numbers from diverse apps like Fountain and Podcast Guru will create a more accurate "tide that lifts all boats" for discovery.
Spotify Editorial Strategy, Podnews Interview and Ranking Systems
A recent Podnews interview with a Spotify executive revealed a highly scripted approach to how shows are spotlighted on the platform. The hosts critique the lack of transparency in Spotify and Apple's editorial processes, suggesting that breaking into these curated lists often requires internal connections rather than algorithmic merit. They argue that editorial curation is inherently subjective and often leads to frustration for independent creators.
Dave Jones explains Low-Rank Adaptation (LoRa) as a parameter-efficient way to fine-tune large language models without retraining the entire base. By adding a small "adapter" of matrices to the serving harness, the model's output can be nudged toward specific expertise, such as identifying slop. This method is more scalable than Retrieval-Augmented Generation (RAG) for high-customization tasks like spam detection.
