Owl-Loving Models: How Hidden Signals Influence Model Behaviour
Registration
Welcome! Please choose your desired ticket type:
About Event
Shivam Arora discusses subliminal learning, a phenomenon where language models learn non-obvious traits from model-generated data. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a "teacher" model that prefers owls. Shivam will explore what subliminal learning means for AI alignment.
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 attend in person, join our live stream starting at 6:30 pm via this link.
Location
30 Adelaide St E
Toronto, ON M5C 3G8, Canada
Enter the main lobby of the building and let the security staff know you are here for the AI event. You may need to show your RSVP on your phone. You will be directed to the 12th floor where the meetup is held. If you have trouble getting in, give Georgia a call at 519-981-0360.