Together, we will be hacking away to demonstrate and mitigate the challenges that arise in the meeting between AI and democracy, while trying to project these risks into the future.

Expose the unknown unknowns of AI model behavior

Co-author research opportunity with Cooperative AI Foundation

Welcome to the research hackathon to devise methods for evaluating the risks of deployed language models and AI. With the societal-scale risks associated with creating new types of intelligence, we need to understand and control the capabilities of such models.

Large AI models are released nearly every week. We need to find ways to evaluate these models (especially at the complexity of GPT-4) to ensure that they will not have critical failures after deployment, e.g. autonomous power-seeking, biases for unethical behaviors, and other phenomena that arise in deployment (e.g. inverse scaling).

Join us for this month's Alignment Jam to investigate how we can both formally and informally verify the safety of machine learning systems!

A weekend for exploring AI & society!

Join us for the fifth Alignment Jam where we get to spend 48 hours of intense research on how we can measure and monitor the safety of large-scale machine learning models. Work on safety benchmarks, models detecting faults in other models, self-monitoring systems, and so much else!

Machine learning is becoming an increasingly important part of our lives and researchers are still working to understand how neural networks represent the world.

Alignment Jam #1