What we’re about
Join us for a variety of events on technical AI safety, governance in a world of advanced AI, and more.
Hosted by Trajectory Labs, a nonprofit coworking and events space catalyzing Toronto's role in steering AI progress toward a future of human flourishing.
Is there a topic you'd love to see us cover at a future event? Submit your suggestion here.
Upcoming events (4)
See all- AI Policy Tuesdays: Agent Governance30 Adelaide East, Industrious Office 12th Floor Common Area, Toronto, ON
Description
Kathrin Gardhouse presents on the nascent field of Agent Governance, drawing from a recent report by IAPS.The presentation will cover current agent capabilities, expected developments, governance challenges, and proposed solutions.
Event Schedule
6:00 to 6:15 - Networking
6:15 to 7:30 - Main Presentation
7:30 to 8:00 - Breakout Discussions - AI Safety Thursdays - Formal Containment: Proof-Carrying Code and AI Safety30 Adelaide East, Industrious Office 12th Floor Common Area, Toronto, ON
Description
AI Safety attention has increasingly shifted toward “defense in depth”: a layered strategy of safeguards.In this context, today's event will have Quinn Dougherty leading us on an exploration of forgotten literature on proof-carrying code to leverage it in a prototype AI containment procedure, enabling a narrow form of enforceable safety.
We'll look at preliminary experimental results, discuss strategic outlook, and cover when proof-carrying code and guaranteed-safe AI more broadly make sense.
Event Schedule6:00 to 6:45 - Pizza & Networking
6:45 to 8:15 - Main Presentation & Questions
8:15 to 9:00 - Breakout Discussions - AI Safety Thursdays: Avoiding Gradual Disempowerment30 Adelaide East, Industrious Office 12th Floor Common Area, Toronto, ON
Description
This talk will explore the concept of gradual disempowerment as an alternative to the abrupt takeover scenarios often discussed in AI safety, and what efforts can be taken to mitigate this risk.We're excited to have guest speaker Dr David Duvenaud to guide us through an examination of how even incremental improvements in AI capabilities can erode human influence over critical societal systems, including the economy, culture, and governance.
Event Schedule6:00 to 6:45 - Pizza & Networking
6:45 to 8:15 - Main Presentation & Questions
8:15 to 9:00 - Breakout Discussions - AI Safety Thursdays: Are LLMs aware of their learned behaviors?30 Adelaide East, Industrious Office 12th Floor Common Area, Toronto, ON
Description
At this event, we'll explore self-awareness in LLMs, as described in the paper Tell me about yourself: LLMs are aware of their learned behaviors. Guiding us through the topic will be one of the paper's co-authors, Jenny Bao.
Event Schedule
6:00 to 6:45 - Networking and refreshments
6:45 to 8:00 - Main Presentation
8:00 to 9:00 - Breakout Discussions
