Event box

Print the page
Add to a Calendar using iCal
Share page on Facebook
This link opens in a new window
Add to Google Calendar
This link opens in a new window
Share page on Twitter
This link opens in a new window
Whose Gold? Re-imagining Alignment for Truly Beneficial AI
Human feedback is often the “gold standard” for AI alignment, but what if this “gold” reflects diverse, even contradictory human values? This keynote explores the technical and ethical challenges of building beneficial AI when values conflict – not just between individuals, but also within them.
This talk by Verena Rieser (Research Scientist at Google DeepMind) advocates for a dual expansion of the AI alignment framework: moving beyond a single, monolithic viewpoint to a plurality of perspectives, and transcending narrow safety and engagement metrics to promote comprehensive human wellbeing.
This event takes place in Lecture Theatre 4. Secure your ticket in advance.
- Date:
- Thursday, October 9, 2025
- Time:
- 13:00 - 14:00
- Time Zone:
- UK, Ireland, Lisbon Time (Change time zone )
- In-Person Events:
- Edinburgh Campus
- Audience:
- All Welcome