







Graze Personalization Engine
For You, For Everyone - Graze Newsletter
How Graze built a "composable personalization" engine for the open social web — and why it matters right now.
Bluesky Custom Feeds - Built By You
Design, deploy, and grow custom feeds of any complexity on Bluesky with Graze.social.

Personalization at Bluesky
The past, present, and future of personalization of the Discover feed


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.

AT Explore
Explore and discover AT Protocol data with our fast, user-friendly browser. Search posts, profiles, and feeds across the decentralized social web — including apps like Bluesky.
atproto-aware concept search engine
a mockup of a webpage search engine that only indexes webpages that are referenced in atproto records. Surfaces related links based on social and community context.
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...


Social Media Analysis - Signup
Plans for everyone! Fedica's free plan allows you to post to many platforms with 1 click, paid plans to supercharge your social media game! Map followers by country, state or city What followers are talking about now

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.
The Sifter - A Food History Research Tool
The Sifter is a public database, free to all users. It is a tool for finding and comparing historical and contemporary writing on food and food-related topics. It is overseen by an advisory board composed of members from The Oxford Symposium on Food and Cookery as well as other friends of food history. As with Wikipedia, the Sifter will be populated by its users. All entries will have an English translation, enabling users to search languages they cannot read. Soon, we will have over 100 languages represented. Registered users will be able to make corrections and add new information. Future releases will include a data visualization component. We also plan to include more resources linking to digitized photographs, artworks, television and film. With the aid of this tool, it is our hope that what has been invisible will come into focus.
The Playoffs On Bluesky, On Leaflet, On Graze and on Open Social - Graze Newsletter
Example Post
Community by Design
Social media empower distributed content creation by algorithmically harnessing "the social fabric" (explicit and implicit signals of association) to serve this content. While this overcomes the bottlenecks and biases of traditional gatekeepers, many believe it has unsustainably eroded the very social fabric it depends on by maximizing engagement for advertising revenue. This paper participates in open and ongoing considerations to translate social and political values and conventions, specifically social cohesion, into platform design. We propose an alternative platform model that includes the social fabric an explicit output as well as input. Citizens are members of communities defined by explicit affiliation or clusters of shared attitudes. Both have internal divisions, as citizens are members of intersecting communities, which are themselves internally diverse. Each is understood to value content that bridge (viz. achieve consensus across) and balance (viz. represent fairly) this internal diversity, consistent with the principles of the Hutchins Commission (1947). Content is labeled with social provenance, indicating for which community or citizen it is bridging or balancing. Subscription payments allow citizens and communities to increase the algorithmic weight on the content they value in the content serving algorithm. Advertisers may, with consent of citizen or community counterparties, target them in exchange for payment or increase in that party's algorithmic weight. Underserved and emerging communities and citizens are optimally subsidized/supported to develop into paying participants. Content creators and communities that curate content are rewarded for their contributions with algorithmic weight and/or revenue. We discuss applications to productivity (e.g. LinkedIn), political (e.g. X), and cultural (e.g. TikTok) platforms.
