Previous Events
AI Control in High Stakes Settings with Aryan Bhatt (Redwood Research)
This talk will provide a concise overview of Redwood Research's foundational AI control research and further research directions. This event is open to anyone. Lunch will be provided, including vegan options.
Careers and Projects in AI Safety with Michael Aird (RAND)
Michael Aird is an associate director of the RAND Center on AI, Security, and Technology. Michael will be giving a talk on planning your career while maximizing your impact, growth, and personal fit. His talks have helped hundreds of people in their transitions to AI safety work and other impactful careers. This event is open to anyone. Lunch will be provided, including vegan options.
Open to all Boston University students, faculty, and staff! Learn about neural scaling laws, why we may build machines smarter than humans (in our lifetime), and why this (might be) problematic. No background experience is required.
Towards Superintelligence, Alignment, and Control (and pizza)
Stephen Casper on Making Robust AI Safeguards Run Deep
Reframing AI safety as a "neverending institutional challenge," Stephen will be presenting his research on designing robust AI safeguards.
Abstract: In 2025, frontier AI developers started warning that their AI systems were beginning to cross risk thresholds related to cyber, chemical, and biological capabilities. This is unfortunate given how closed-weight AI systems are persistently vulnerable to prompt-injection attacks and open-weight systems are persistently vulnerable to malicious fine-tuning. This presentation will focus on tools for making frontier AI safeguards “run deep.” In particular, we will focus on technical tools for safeguarding open-weight systems. Finally, we will discuss the challenge of making AI safeguards research matter in the real world. Along the way, we will discuss what AI safety can learn from the design of lightbulbs and why you should keep a close eye on Arkansas Attorney General, Tim Griffin, in 2026.
2026 Boston
AI Safety Mixer
Q&A with Colorado Representative
Brianna Titone
Join Colorado Representative Brianna Titone for a discussion on the making of SB24-205, the Consumer Protections for Artificial Intelligence Bill, which recently went into effect. As one of the bill’s prime sponsors, Representative Titone will share her experience helping shape and advance the legislation, as well as her perspective on the broader challenges of regulating artificial intelligence.
