ControlConf is a conference dedicated to the emerging field of AI control: the study of techniques that mitigate security risks from AI even if the AI itself is trying to subvert them.

When: March 27–28, 2025
Where: Marylebone, London

A collaboration between Redwood Research, FAR.AI, and the UK AI Security Institute, ControlConf will bring together individuals interested in AI control (introduced here and here), including:

• Researchers actively working on AI control at frontier labs, government departments, nonprofits, academia, and elsewhere
• AI researchers who want to learn more about AI control but lack direct experience
• People approaching AI control from non-AI backgrounds—such as information security professionals, policy researchers, and others who are interested in strategies to mitigate catastrophic misalignment risk

Our main objectives are:

1. Coordination
   Many people are now exploring AI control, so we aim to foster discussion on core strategic questions like “How ambitious should control strategies be?” and “What research is most pressing right now?”
   
   

2. Knowledge Sharing
   As many individuals are new to the field, or have yet to engage with it directly, this conference will help participants understand the state of the field.
   
   

3. Interdisciplinary Discussions
   We’ll explore AI control issues with experts from related areas, including AI policy and information security, to bring broader perspectives into the discussion.

Conference content will feature a mix of presentations, demos, panel discussions, opportunities for one-on-one conversations, and structured breakout sessions.

If you’re interested in attending, please fill out the expression of interest form by March 7.

Expression of Interest

Established in February 2023, the Alignment Workshop convenes top ML researchers and practitioners from industry, academia and government to discuss and debate topics related to AI alignment. We aim to enable researchers to better understand potential risks from advanced AI, and strategies for solving them. Key issues discussed include model evaluations, interpretability, robustness and AI governance.

You can learn more about the series on the workshop website, or watch videos from previous workshops on our YouTube channel.

We will have three Alignment Workshops in 2025:

• Singapore (April 23rd, next to ICLR 2025)
• London (independent)
• San Diego (next to NeurIPS 2025)

If you’d like to attend any of these workshops or future events, please fill out our Expression of Interest. We look forward to seeing you soon!

Watch videos from previous workshops Expression of Interest

The International Dialogues on AI Safety (IDAIS) bring together senior computer scientists and AI governance experts to build international collaboration on minimizing extreme AI risks. The first event in the series was hosted in Oxfordshire, UK in October 2023, the second in Beijing, China in March 2024, and the third in Venice in September 2024. A fourth dialogue is planned for early 2025.

The project is supported by the Safe AI Forum, co-founded by Fynn Heide and Conor McGurk in late 2023.

Visit the IDAIS website Visit the SAIF website Contact the SAIF/IDAIS team