Top all-time · #7963
Spotify Research
Company blog · research.atspotify.comaidata
Spotify Research is the company blog at research.atspotify.com, writing about ai and data. Since 2021, 10 different Hacker News readers have linked it 14 times, most often “LLark: A Multimodal Foundation Model for Music”. It is still writing: the last post was on 2026-10-21, and you can follow it by feed.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link Spotify Research's blog and publications as a source on how Spotify models users and makes recommendations, and as a pointer to its audio tooling research. Comments cite it rather than judge it.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Our Research teams share updates dedicated to extending the state of the art in audio and video. AI, Speech and NLP, Economics, Causal Inference, Algorithmic Responsibility, and more.
Most-linked posts?
- LLark: A Multimodal Foundation Model for Music2 people · 2 mentions · first linked 2023-10-13
What Hacker News says?
They spend a lot of effort trying to get good at predicting user preferences, through modeling of personality, behaviour patterns and more. You can find out quite a lot in their blogs and publications: https://research.atspotify.com/2022/02/modeling-users-accord... https://research.atspotify.com/user-modeling/
Comment linking /user-modeling/
on “Senior Developer Skills in the AI Age”Submitted The Dynamics of Music Exploration on Spotify as a story · 81 points
HN discussionThere is! Check out http://research.atspotify.com/ .
Comment linking /
on “Pedalboard: Spotify’s Audio Effects Library for Python”Submitted Personalizing Agentic AI to Users' Musical Tastes as a story · 2 points
HN discussionHere https://research.atspotify.com/2024/12/contextualized-recomm... ;)
Comment linking /2024/12/contextualized-recommendations-through-personalized-narratives-using-llms/
on “Everything we announced at our first LlamaCon”Submitted LLark: A Multimodal Foundation Model for Music as a story · 2 points
HN discussionI have no specific insider knowledge, but a decade+ ago they bought a company called the Echo Nest that was developing some of the best audio signal analysis algorithms around, I assume much of that influenced their recommender system. Nowadays, they have a quite busy research department so I would imagine that recommendation is quite fancy indeed: https://research.atspotify.com
Comment linking /
on “The lie of music discovery algorithms”Submitted Automatic Music Playlist Generation via Simulation-Based Reinforcement Learning as a story · 2 points
HN discussionSubmitted Podtile: Podcast Episode Browsing with Auto-Generated Chapters as a story · 1 points
HN discussionSubmitted What the Hype and Reality of Agents: Resurgence of the Past, with LLM Flavors as a story · 1 points
HN discussionSubmitted Spotify's LLark: A Multimodal Foundation Model for Music as a story · 1 points
HN discussionSubmitted Representation of Music Creators on Wikipedia, Differences in Gender and Genre as a story · 1 points
HN discussionSubmitted Users’ interests are multi-faceted: recommendation models should be too as a story · 1 points
HN discussion