You can't DDoS the Fediverse!
The Atmosphere really needs to invest in making it easier to set up a more diversified ecosystem.
Posts by Andrés Monroy-Hernández
If you're at #CHI26 like most of CITP this week, be sure to check out postdoctoral researcher Sohyeon Hwang's (@s0hw.bsky.social) presentation "Community Governance and Moderation" on Friday morning 🔻
📲 Researchers at @princetoncitp.bsky.social have created a social media tool that allows users to build their own social media feeds from scratch.
Meet Bonsai. 🌳
🏃♀️ homestretch! start your last day at #CHI2026 at the "Community Governance and Moderation" 9AM session tomorrow in Room 114 🤠 I'll be presenting our new work envisioning how we can make community-run social media more sustainable through a "community of communities": dl.acm.org/doi/10.1145/...
4 people sitting and looking at cell phone screens while smiling
What if you could have more agency over your social media feed? CITP researchers have built Bonsai to explore what happens when users can have that control. Try the app now on @bsky.app! getbonsai.org
Team: @manoelhortaribeiro.bsky.social @andresmh.com @mariannealq.bsky.social Omar El Malki
First page of the paper titled Bonsai: Intentional and Personalized Social Media Feeds. Image shows pipeline with steps: Plan, Source, Curate, Rank.
The full paper is available in the ACM DL dl.acm.org/doi/pdf/10.1...
Massive kudos to the awesome @omelmalki.bsky.social, who was able to build this in a summer.
Hey Bluesky friends, please check out and let us know what you think of 🌳 Bonsai, a new tool to create custom Bluesky feeds getbonsai.org
Story: www.cs.princeton.edu/news/what-ha...
Presented at #CHI2026 by @manoelhortaribeiro.bsky.social and @mariannealq.bsky.social
New in #TOCHI
FairFare (arxiv.org/pdf/2502.11273) a crowdsourced data tool co-designed with a Colorado rideshare union to audit platform take rates from 76k+ rideshare trips.
Authors: Dana Calacci, Varun Rao, Samantha Dalal, Kok-Wei Pua, Andrew Schwartz, Danny Spitzberg, Andrés Monroy-Hernández
Participate in a fun study from one of our students that involves creating your own daily email digest to catch up on what happened on Bluesky!
Thursday 3/5 at 2:00 - 3:00pm Claudia Lo of @wikimediafoundation.org will be a special guest at Professor Andrés Monroy-Hernández's (@andresmh.com) class 🔻
Open to Princeton U faculty, staff, and students.
📍Sherrerd Hall, 306
A search for factors for algorithm understanding results in multiple terms displayed as documents, including available, compact, and aligned. These are shown to be necessary and sufficient. Other, similar terms are shown in the background faded, like intuitive, rule-based, grounded, modular, linear, decomposable, accurate, symbolic, causal, and personalized.
Is the only way we can create algorithms that people understand to make them trivially simple? We argue, no.
People can predict the behavior of algorithms that are arbitrarily complex, if and only if they are available, compact and aligned.
arxiv.org/abs/2601.18966
A fundamental challenge in human-robot interaction is that capabilities and limitations are often opaque to users.
In our upcoming #HRI2026 paper, X-OOHRI, led by the brilliant Lauren Wang, we use AR to make robot capabilities and limits visible during object-oriented interactions 🤖
A new app developed at @princetoncitp.bsky.social allows researchers to construct a large-scale dataset that aggregates individual worker data across many thousands of rides to shed light on the working conditions of rideshare drivers.
help spread the word about this campaign - or, if you're able, consider supporting yourself! Bonfire is building a modular toolkit for organizing, mutual aid, open science, and collective decision-making on the open social web. communities choose what gets built:
www.indiegogo.com/en/projects/...
CITP is hiring for the 2026 academic year. The list of advisors is now available on the CITP Blog: blog.citp.princeton.edu/2025/11/06/c...
▶️ Postdocs
▶️ Visiting Professor
▶️ Visiting Professional
▶️ Emerging Scholars
The DeCenter at Princeton is hiring a cohort of postdocs to work on decentralization of power through decentralization of trust. HCI folks encouraged to apply puwebp.princeton.edu/AcadHire/app...
We implemented Bonsai on Bluesky and conducted a two-phase, multi-week study with 15 participants. This deployment allowed us to observe how people used intentional feedbuilding in practice, and how it compared to their experiences with engagement-driven defaults.
In the ranking stage, Bonsai orders the curated content using criteria derived from the user’s stated intent—rather than predicted engagement—making the logic behind feed prioritization transparent and directly aligned with user goals.
In the curating stage, users can apply natural language prompts (e.g., “focus on recent policy updates” or “exclude promotional posts”) to filter and organize the sourced content, ensuring the feed reflects users' goals / preferences. Each prompt is fed into an LLM that individually ranks content.
In the sourcing stage, Bonsai gathers a wide pool of candidate posts aligned with user goals. Users can refine this stage by editing sources (adding or removing accounts, hashtags, or feeds) to shape where their feed draws content from.
In the planning stage, users express their goals in natural language (e.g., “updates on AI policy” or “posts from close colleagues”). Bonsai translates these goals into structured representations that guide the subsequent sourcing, curating, and ranking of content by providing initial suggestions.
With Bonsai, users can articulate what they want from their feeds (e.g., tracking research, staying informed on a policy area, or connecting with a community) and the system procedurally builds a feed that reflects those intentions in four steps, which we discuss below.
Bonsai sits within a broader debate on recommender systems. While TikTok or Meta optimize (mostly) for attention capture, Bonsai explores what feeds look like when personalized for user intent. Under our taxonomy, it explores the design space of "intentional" and "personalized" feeds!
Social media feeds today are optimized for engagement, often leading to misalignment between users' intentions and technology use.
In a new paper, we introduce Bonsai, a tool to create feeds based on stated preferences, rather than predicted engagement.
arxiv.org/abs/2509.10776
Finally, @princeton.edu is on a decentralized social media platform! 👏👏
A faded etching of the Hudson River from Hoboken is overlaid with the following text: CSCW Northeast 2025, in-person regional gathering. Friday, October 3, 2025, 10AM-4:30PM at University Center Complex, Stevens Institute of Technology. RSVP: cscw-ne.hci.social The logos of HCI at Stevens, Princeton HCI, and Rutgers University are on the right-hand side.
I'm co-organizing #CSCW NE, an in-person regional gathering for people in Northeast America, alongside some folks from Stevens, Rutgers, and Princeton. If you want to come hang out (especially if you can't make it out to the full conference in Bergen this year), RSVP at cscw-ne.hci.social!
🚨 Study alert!
We've developed a prototype that enables you to create personalized social media feeds using natural language rules and import them into Bluesky.
Join our study to try out the tool, give us your feedback, and earn a $50 gift card!
Sign up: forms.gle/MkSGKzxDfBEc...
Please share :)
One of the great things about decentralized social media is that researchers can experiment with new ideas.
Please help science and apply to be part of this study that one of our students is doing to make it easier for anyone to create sophisticated custom Bluesky feeds.
Spread the word too! 🙏
on one side, tesla stock falling while trump and elon beef. on the other side, request rates to a bsky service rapidly increasing
"huh is something going on?"
"oh"