Events
/
FAR.AI Seminar

Weekly insights from leading experts in trustworthy & secure AI

The FAR.AI Seminar is a weekly event series hosted in Berkeley at FAR.Labs and streamed remotely, featuring presentations from prominent researchers in trustworthy & secure AI. Previous speakers include leading academic and industry experts like Yoshua Bengio, Nicholas Carlini, and Ethan Perez.

Seminar PlaylistAll recordings

Watch seminar videos

View a selection of our seminars here, or view our YouTube playlist.

Plan B: Training LLMs to fail less severely

Julian Stastny presented "Plan B: Training LLMs to fail less severely" at FAR.Labs, as part of the FAR.AI Seminar series.

Eliciting the capabilities of scheming LLMs

Fabien Roger presented "Eliciting the capabilities of scheming LLMs" at FAR.Labs, as part of the FAR.AI Seminar series.

3 Mechanisms Underlying Emergent Abilities in Generative Models

Hidenori Tanaka (Harvard) presented "3 Mechanisms Underlying Emergent Abilities in Generative Models," linking AI creativity and safety with insights from physics, neuroscience, and psychology.

Campaigns in Emerging Issues: Lessons Learned from the Field

How can strange bedfellows shape the future of AI policy? Andrew Freedman, founder of fathom.org, shares lessons from cannabis regulation to build unlikely coalitions for AI governance.

Deceptive Instrumental Alignment

Evan Hubinger dives into “Deceptive Instrumental Alignment,” revealing how AI might appear aligned during training while secretly harboring harmful intentions for deployment.

Verification & Confidence Building for International Coordination

Peter Barnett describes the potential of hardware enabled mechanisms to provide verification and confidence to international coordination schemes for AI.

Modeling and Mitigating Near-term Deployment Risks from LLMs

Alex Pan discusses strategies for modeling and mitigating immediate deployment risks associated with large language models (LLMs).

Simplex

Paul Riechers and Adam Shai, founders of Simplex, discuss their approach to developing a principled science of AI cognitive capabilities and associated risks.

Formal AI-Assisted Code Specification and Synthesis

Shaowei Lin discusses formal methods in AI-assisted code specification and synthesis, emphasizing formal verification as a strategy to protect sociotechnical systems from human-led and AI-enabled attacks.

Defending Against Adversarial Attacks in Go

Can Go AIs be adversarially robust? Tom Tseng explores defending Go bots against adversarial attacks, using adversarial training and architecture change.

Category Theory

Kris Brown Brown discusses the role of category theory in creating interpretable and adaptable AI systems, aiming for enhanced safety and stakeholder alignment.

How Could We Design Aligned & Provably Safe Al?

Pioneering AI researcher Yoshua Bengio explores approaches to designing AI systems that are both aligned with human values and provably safe.

Sleeper Agents

Ethan Perez shows how large language models can hide harmful behaviors, even under safety training.
Subscribe to our newsletter
Organization
AboutTeamProgramsNewsSearch
Events
All EventsAlignment WorkshopsIDAISSpecialized WorkshopsAll Event Recordings
Research
All PublicationsResearch Overview
Robustness
Interpretability
Model Evaluation
Get involved
CareersContactDonateNewsletter
Financial Reports / 990sPrivacy PolicyTerms of Service

Cookies Notice: This website uses cookies to identify pages that are being used most frequently. This helps us analyze web page traffic and improve our website. We do not and will never sell user data. Read more about our cookie policy on our privacy policy. Please contact us if you have any questions.

© 2025 FAR AI, Inc.
Website by ODW
FAR.AI only uses cookies essential for website functionality and anonymous usage analytics.
I understand
View Privacy Policy to learn more.