Past Events
Here are some of the past events that we have had!
27 Feb 2025
Launch Party
We hosted a launch party with more than 70+ attendees and had our members give lightning talks to share about the work that they did.
13 March 2025
International AI Governance: Key Challenges and Solutions
Visiting analyst, Su Cizem from Centre pour la Sécurité de l'IA - CeSIA, gave a talk on “International AI Governance: Key Challenges and Solutions”
20 March 2025
Can incomplete preferences keep artificial agents shutdownable?
Visiting research fellow, Elliott Thornley from Oxford University, gave a talk on “Can incomplete preferences keep artificial agents shutdownable?”
27 March 2025
Paper Club: AI Control — Safety Beyond Alignment
We had a paper club on the topic of "control evaluations," which test whether safety protocols remain effective when AI systems intentionally attempt to subvert them.
28 March 2025
AI Control Hackathon 2025
The Control Hackathon by APART Research is a global hackathon which focuses on techniques that mitigate security risks from AI, even when the AI itself might be trying to subvert them. We were the Singapore jam site for the hackathon.
17 April 2025
Paper Club: Looking inside Claude’s “Brain”
We had a paper club where we explored Anthropic’s groundbreaking research paper, “On the Biology of a Large Language Model.” This fascinating study applies neuroscience-inspired techniques to peek inside Claude 3.5 Haiku and understand how it actually “thinks.”
27 April 2025
AI Safety Networking Social
Together with Concordia AI, FAR.AI and Safe AI Forum, we organised a networking social with 130+ attendees from around the globe - researchers, builders and policymakers all working on safer AI.