A community at the University of Wisconsin dedicated to mitigating the risks of transformative AI.
Our Mission
We believe that AI presents a magnitude of risks and benefits unmatched by any previous technology. To realize the benefits, we must address the risks.
We contribute by:
- —Building and supporting a community of AI Safety specialists.
- —Producing impactful research across disciplines.
- —Informing public discourse on transformative AI.
Our goal: help humanity navigate the transition to advanced AI wisely.
"It's been great working with everyone and getting to be around people who are really interested in AI Safety and helping people get involved. It's exciting to be a part of this."
— Shawn Im, PhD Student
- 10 PhD Safety Scholars
- 6 Masters Safety Scholars
- 50+ Undergraduate Safety Scholars
- 30 Current AI Safety Fundamentals participants
- 130+ AI Safety Fundamentals graduates
"...A year ago the idea of facilitating a group discussion would've been hugely intimidating to me but now I find myself looking forward to my cohort sessions. This much needed nudge out of my comfort zone has shaped my growth as a leader and student..."
— Elise Fischer, Policy Team
- —Nine members flown to Washington, DC to present at a Congressional Exhibition on Advanced AI.
- —Contributed to Wisconsin's 2023 Assembly Bill 664 on AI disclosure in political ads.
- —Hosted speakers from Google DeepMind, Anthropic, METR, CNAS, and the Horizon Institute for Public Service
Research Highlights
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
Our Members Have Collaborated With
Our Sponsors
Kairos
UW-Madison Computer Sciences