# Tianyi Alex Qiu | Computing Human Ideal Preference, Breaking AI Feedback Loops

- **When:** Fri, Dec 18, 2026, 10:00 AM PST – 11:00 AM PST
- **Where:** Online
- **Price:** $10 (approval required)
- **Organizer:** [Lydia La Roux](https://eventing.ing/organizers/orgz_1m1k90sev9bwt5qnceb89b)
- **Categories:** AI & ML
- **Get tickets on Luma:** https://luma.com/1nak2raq

Foresight Institute’s Computation Group

Computing Human Ideal Preference, Breaking AI Feedback LoopsAbstract: How should an AI system assist someone whose beliefs and preferences are still forming while under the influence of such AI systems? Classical approaches based on preference learning and inverse reinforcement learning often mistake transient/instrumental preferences (e.g., money) for stable/terminal ones (e.g., well-being). The latter is stationary while the former…

Source: Luma. Eventing indexes this event and links to the source for tickets and the full description.

Same event as JSON: https://api.eventing.ing/events/evnt_1m2z1rdye8tgz88zjng0jf