AI Safety Thursday: Claude's New Constitution

​On January 21st, Anthropic released a new "Claude Constitution", a document intended to govern the behaviour of their AI model Claude. Giles Edkins will explore this new document: what's in it, how it is used in training, and how well Claude's real world behaviour has stacked up against these ideals.

​​​​Event Schedule
6:00 to 6:30 - Food and introductions
6:30 to 7:30 - Presentation and Q&A
7:30 to 9:00 - Open Discussions

​​​​​​​If you can't make it in person, feel free to join the live stream starting at 6:30 pm, via this link.

​​​​This is part of our weekly AI Safety Thursdays series. Join us in examining questions like: 

• ​​​​How do we ensure AI systems are aligned with human interests? 

• ​​​​How do we measure and mitigate potential risks from advanced AI systems? 

• ​​​​What does safer AI development look like?