Herbert Wertheim College of Engineering
Renwick Program for Safe, Ethical and Beneficial AI
Led by Sonja Schmer-Galunder · Computer and Information Science and Engineering
What we study
The lab studies AI ethics, safety, and governance, using cultural frameworks and interdisciplinary approaches. Projects include moderating hate speech, analyzing bias in language models, and global AI partnerships.
What working here is like
- Computational
- Reading, writing & theory
- Coding helps
- Projects
- 2
- Papers
- 4
Current projects
DARPA Civil Sanctuary
Uses AI to moderate hate speech and promote prosocial discourse.
DARPA HABITUS
Applies anthropological methods to study cultural values in AI decision-making.
Summaries are written by AI in plain language from public symposium abstracts and may be imperfect.
Recent papers, explained
- Culture in the code: Anthropological Concepts Decoding AI’s Hidden Assumptions
2026 · AI and Ethics
- Anthropology for AI
2025 · University of Zagreb University Computing Centre (SRCE)
Applies anthropology concepts to AI, arguing that alignment problems stem from cultural assumptions about human behavior.
Show 2 more papersShow fewer
- Information architectures: a framework for understanding socio-technical systems
2025 · npj Complexity
Explores how information architectures shape societal interactions through physical, digital, and algorithmic systems.
- Is from ought? A comparison of unsupervised methods for structuring values-based wisdom-of-crowds estimates
2024 · Journal of Computational Social Science
Plain-language summaries are AI-written and reviewed by us; check the paper for details.
How to reach out
Sonja Schmer-Galunder hasn't set up this page yet. You can also look them up in the UF directory (search “Sonja Schmer-Galunder”).