FAR Seminar

Berkeley, CA

January 1, 2024
Date Range

Overview

FAR.AI’s weekly seminar series brings together leading voices in AI safety to share cutting-edge research and insights at FAR.Labs in Berkeley. Past speakers include luminaries such as Anca Dragan, Sam Bowman, and Yoshua Bengio, offering a unique opportunity for attendees to deepen their understanding of AI alignment and governance. Join us to explore the frontiers of safe and beneficial AI alongside world-class experts.

FAR Seminar sessions

Low probability estimation

Jacob Hilton

October 28, 2025

2025

Can you just train models not to scheme?

Marius Hobbhahn

October 7, 2025

2025

Singular Learning Theory and AI Safety

Jesse Hoogland

September 16, 2025

2025

What Would it Take to Stop the Development of Superintelligence? A Treaty Proposal

Aaron Scher

August 26, 2025

2025

The EU Code of Practice: Towards a Global Standard for Frontier AI Risk Management

Siméon Campos

August 19, 2025

2025

Alignment is social: lessons from human alignment for AI

Gillian Hadfield

August 5, 2025

2025

Realigning AI

Zhijing Jin

June 17, 2025

2025

The Role of AISIs in AI Governance

Rob Reich

March 11, 2025

2025

Plan B: Training LLMs to fail less severely

Julian Stastny

February 4, 2025

2025

Eliciting the capabilities of scheming LLMs

Fabien Roger

January 14, 2025

2025

3 Mechanisms Underlying Emergent Abilities in Generative Models

Hidenori Tanaka

October 22, 2024

2024

Campaigns in Emerging Issues: Lessons Learned from the Field

Andrew Freedman

August 27, 2024

2024

Deceptive Instrumental Alignment

Evan Hubinger

July 30, 2024

2024

Verification & Confidence Building for International Coordination

Peter Barnett

July 23, 2024

2024

Modeling and Mitigating Near-term Deployment Risks from LLMs

Alex Pan

July 13, 2024

2024

Simplex

Multiple Speakers

June 25, 2024

2024

Formal AI-Assisted Code Specification and Synthesis

Shaowei Lin

May 21, 2024

2024

Defending Against Adversarial Attacks in Go

Tom Tseng

April 30, 2024

2024

Category Theory

Kris Brown

April 28, 2024

2024

How Could We Design Aligned & Provably Safe Al?

Yoshua Bengio

April 16, 2024

2024

Sleeper Agents

Ethan Perez

February 14, 2024

2024