☀️ For the 2nd year in a row, I had the honor of serving as Student Volunteer Co-Chair, leading an incredible team of over 200 SVs at @chi.acm.org
My heartfelt thanks go out to our SVs, the true MVPs who work tirelessly behind the scenes. We hope all attendees had a wonderful conference!
Finally, we also had a paper with collaborator @tskuo.bsky.social at CMU on enabling collective design of community bots via a system that surfaces provocative hypothetical cases as a way to stress-test and iterate on bot policy: arxiv.org/abs/2509.25492
AI agents, or bots, serve important roles in online communities. However, they are often designed by outsiders or a few tech-savvy members, leading to bots that may not align with the broader communit...
12/ During a field deployment across six Discord communities, Botender supported community members in tailoring bot behavior to their specific needs, showcasing the usefulness of case-based provocations in facilitating collaborative bot design.
7/ To address these challenges, we present Botender, a system that supports communities in collaboratively designing LLM-powered bots that reflect their specific needs.
With Botender, community members can directly propose, iterate on, and deploy custom bot behaviors on their community platform.
