All sprints

Join us to investigate and understand multi-agent security (MASec) in frontier AI!

Join us to work with engaged individuals across the globe on the most important questions of AI governance.

Join us with Apollo Research to expose the ways artificial intelligence can be high-risk in the real world!

​Will you be one of the 40 most exceptional AI/ML engineers, researchers or students passionate about this field to take part in our next AI Safety Hackathon in the Netherlands?

As AI systems proliferate and become increasingly agent-like, they will interact with each other and with humans in new ways. These new multi-agent systems will create entirely new risk surfaces.

The agency foundations challenge is hosted by agencyfoundations.ai and explores how IRL/RL, game theory and mechanistic interpretability can help preserve human agency in the quest for and in the presence of superhuman intelligent AI systems. Join for the kickoff hackathon happening the 8th to 10th of September.

Join us for the Distillation Hackathon where you are tasked with working on more digestible versions of existing literature in AI safety research and theory!

Evaluating large models is becoming more and more important. In this research sprint, we find more and better ways of evaluating large models before they are deployed. Join us!

Interpretability is becoming a more and more promising field of research to understand and reverse-engineer what the black boxes of neural networks learn. Join us with some of the top researchers in mechanistic interpretability!

It is becoming more and more important to understand the safety of state-of-the-art machine learning systems, especially language models. Join us for a weekend to come up with ideas and demos for new benchmarks for safety.

Join us for the Distillation Writathon where you are tasked with writing more digestible versions of existing literature in AI safety research and theory!

The ARENA research training program is hosting an interpretability hackathon in London.

Join the AI safety research hackathon happening right after EAGx LatAm! The topic will be about researching and understanding trends within AI development. Jaime Sevilla and the Epoch team will join as judges and mentors for the duration of the event.