College of Engineering, Design & Computing Events

Funder: Open Philanthropy

At Open Philanthropy, we think the possibility of transformative AI is worth taking seriously and planning for right now. In particular, we should prepare for the risk that AI systems could be misaligned — that they might pursue goals that no one gave them and harm people in the process. We think that ML research today can help to clarify and mitigate the likelihood of this failure mode.

Research areas:

• Adversarial machine learning
• Exploring sophisticated misbehavior in LLMs
• Model transparency
• Trust from first principles
• Alternative approaches to mitigating AI risks