John Burden
CSER, University of Cambridge
Why do you care about AI Existential Safety?
Artificial Intelligence has enormous potential to reshape the world around us and provide immense benefits
for all of humanity. At the same time, AI could present an unprecedented level of risk and danger to life on Earth. Balancing these risks and benefits looks to be an incredible challenge that will likely have far reaching consequences.
Please give one or more examples of research interests relevant to AI existential safety:
I’m broadly interested in the following areas:
- Reducing the likelihood of negative side effects caused by AI systems.
- Understanding how we can better evaluate AI systems to determine their capabilities and the range of tasks they can perform.
- Identifying AI system vulnerabilities and risks in order to address them.