Sign up to save your podcasts
Or
Share Episode 13 | Nell Watson | Author and AI Safety Researcher
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Episode 13 | Nell Watson | Author and AI Safety Researcher
AI doesn’t just fail. It can malfunction in predictable and dangerous ways.
In this episode of Trustworthy AI Chronicles, Dr. Ihsen Alouani sits down with Nell Watson, Author and AI Safety Researcher, to explore how we diagnose, govern, and build trustworthy AI systems.
They explore AI “pathologies,” artificial sanity, and why we may need to treat AI systems more like minds than machines. Nell shares insights from her work developing global standards, teaching ethics to machines, and building safer agentic AI.
Will AI help amplify our best instincts…or our worst?
Follow CSIT on LinkedIn for more: https://www.linkedin.com/company/csit-qub
View all episodes
By The Centre for Secure Information Technologies (CSIT)AI doesn’t just fail. It can malfunction in predictable and dangerous ways.
In this episode of Trustworthy AI Chronicles, Dr. Ihsen Alouani sits down with Nell Watson, Author and AI Safety Researcher, to explore how we diagnose, govern, and build trustworthy AI systems.
They explore AI “pathologies,” artificial sanity, and why we may need to treat AI systems more like minds than machines. Nell shares insights from her work developing global standards, teaching ethics to machines, and building safer agentic AI.
Will AI help amplify our best instincts…or our worst?
Follow CSIT on LinkedIn for more: https://www.linkedin.com/company/csit-qub