Fourth post in this series on personalized recommendations
Bluesky "For You" feed playground
This page shows recommendations generated by the For You custom feed. The algorithm has three simple steps:
Paper Skygest: Personalized Academic Recommendations on Bluesky
We build, deploy, and evaluate Paper Skygest, a custom personalized social feed for scientific content posted by a user's network on Bluesky and the AT Protocol. We leverage a new capability on...
Michael Tsai - Blog - App Store Personalized Recommendations and Keylogging
This week, Apple announced a series of discovery features that will personalize app recommendations based on users’ interests and behavior, providing a new way for developers to have their app discovered.
Hardcover
We're a social network for book lovers to find life changing books, track what you read & want to read, and connect with passionate readers.
Personalization at Bluesky
The past, present, and future of personalization of the Discover feed
The Magic of Small Databases
Notes on personal libraries, collections and small indexes on the web
Top2Vec: Distributed Representations of Topics
Topic modeling is used for discovering latent semantic structure, usually referred to as topics, in a large collection of documents. The most widely used methods are Latent Dirichlet Allocation and Probabilistic Latent…
Sensors, not just bookmarks [Patterns of Sensemaking #1] - Cosmik Labs
First of a new series on sensemaking patterns we're observing on Semble
Standardizing Bookmarks in the Atmosphere · Wesley's notes
a mini proposal for a shared bookmark lexicon
Design intuitive search experiences - WWDC26 - Videos - Apple Developer
Explore new patterns and best practices when implementing search in your app. Discover how search plays a key role in helping people find...
Thoughts on Bookmarking the Web - Henrique Dias
Yesterday I shared some atmospheric thoughts. One of the ideas was seeing which services do I use now that could be replaced. One of those is bookmarking. There’s two main contenders: Margin and Semble.
"Save for Later" Has No Later
"Save for Later" Has No Later
Letting things build
This week I put together a reading list for my digital aura series. I recall starting to write around Thanksgiving — but when I looked back at my reading, I’d started reading for it months earlier. (No wonder it’s felt like such a big endeavor!)
Guardian Angels: LLM Personalization for Productivity and Security
I propose an approach for highly personalized LLMs, for near-future productivity gains and personal info/cybersecurity against increasingly powerful LLMs: they should, in the spirit of uploading, try to emulate the user’s values and preferences in order to amplify the principal—not replace them. I discuss a package of techniques and proposals to accomplish such ‘guardian angels’; dynamic evaluation of LLMs combined with active learning and elicitation and heavy inner-monologue search/data-augmentation.
