

Evgenii Opryshko explains how we currently teach AI systems to be helpful, honest, and harmless. The talk covers RLHF, RLAIF, Constitutional AI, deliberate alignment, and other approaches used by frontier AI companies and open-source projects to align language models with human values.
βEvent Schedule6:00 to 6:30 - Food and introductions6:30 to 7:30 - Presentation and Q&A7:30 to 9:00 - Open Discussions
ββββIf you can't attend in person, join our live stream starting at 6:30 pm via this link.
ββββThis is part of our weekly AI Safety Thursdays series. Join us in examining questions like:
ββββHow do we ensure AI systems are aligned with human interests?Β ββββHow do we measure and mitigate potential risks from advanced AI systems?Β ββββWhat does safer AI development look like?
Sign in to view full event details
Create a free account to see descriptions, save events, and more
Teaching Human Values to AI Systems is a independent taking place on Thursday, April 23, 2026 at 30 Adelaide St E, Toronto, ON M5C 3G8, Canada, Toronto, Canada. This independent is organised by Trajectory Labs. This event is priced up to cad 5.
Join this independent over 3 hours for an engaging session of learning, discussion, and networking with fellow attendees.
This independent in Toronto is ideal for:
This evening independent is part of the growing events scene in Toronto. Whether you're based in Toronto or visiting for the independent, it's a great opportunity to connect with the local community. Browse more upcoming events in Toronto on Rifio.
Teaching Human Values to AI Systems covers topics including AI. Find similar events by browsing these topics on Rifio.