Talks
Public talks and lectures from researchers and practitioners working on AI safety, governance, and policy.
Events
SASH convenes researchers, policymakers, and practitioners through formats built for serious exchange: briefings, workshops, paper clubs, public talks, and private meetings.
Event Formats
Some formats are public, some are private. Each is built around research or policy work that needs a room.
Workshops
Hands-on sessions, paper clubs, and close reading sessions for technical and governance topics.
Convenings
Private meetings for senior researchers, institutional partners, and government officials.
Briefings
Policy and technical briefings for government partners and the Singapore field.
Past Events
Closed-door Roundtable: Detecting and Disrupting AI Agent Cyberattacks
Based on a forthcoming report with CSA, the roundtable will bring together government officials from multiple AISIs, cybersecurity industry practitioners, and AI security researchers to develop concrete approaches to...
AI Safety x Cybersecurity Meetup
Interested in the intersection of AI Safety and Cybersecurity?
Women in AI Safety
In celebration of International Women's Day, we are having a Women in AI Safety event!
AI Control Hackathon - Singapore
This is the Singapore edition of the AI Control Hackathon.
A Fireside Chat with BlueDot Impact
Curious to find out more about how to contribute to AI Safety?
Fireside Chat on AI Policy
Curious to find out more about AI Policy?
Office Hours with Joping from Apollo Research
Are you working on AI Safety research or interested in AI Safety research?
Inflection Point
We are approaching a critical threshold in model capabilities.
Singapore AI Safety Social
Come to network with people in the AI Safety space. Join us if you are working on technical AI safety or AI governance, or if you are interested to find out more!
Singapore Consensus on AI Safety Priorities - Discussion Workshop
As AI capabilities advance rapidly, which safety priorities matter most?
AI Safety Meetup Singapore
Concordia AI, FAR.AI and the Singapore AI Safety Hub are jointly organising an AI Safety Meetup on 14 November, 7-9pm.
High level introduction to Technical AI Safety
We're hosting an introductory session on technical AI safety: covering the fundamentals of how LLM models are trained, potential failure modes, and why AI safety is important.
AI-accelerated biological risk: Delving into Asia's challenges and emerging solutions
As AI-enabled biodesign accelerates, so do the questions around responsible development, risk mitigation, and international cooperation.
AI Governance in Singapore
Concordia AI, with support from the Singapore AI Safety Hub, is organising "AI Governance in Singapore".
Paper Club: Memory, Modularity, and Safety
Technical Note: This event is intended for participants with a technical background.
Online AI Safety Talk - Beyond Human Wisdom: Can We Survive the Rise of AGI?
Beyond Human Wisdom: Can We Survive the Rise of AGI?
AI Governance Talk - Effective Governance and State of AI Safety in Singapore
First Talk: How effective governance creates better outcomes for AI
Paper Club: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Technical Note: This event is intended for participants with a technical background.
AI Safety Meet-Up Singapore
Join us for our first community event in Singapore!
AI Governance Talk - Truth, Trust, and Tech: Governing Generative AI for a Safer Digital Future
First Talk: AI Governance Talk - Truth, Trust, and Tech: Governing Generative AI for a Safer Digital Future
Paper Club: Preference Learning with Lie Detectors can Induce Honesty or Evasion
Technical Note: This event is intended for participants with a technical background.
AI Safety x Physics Hackathon
This event is part of a global initiative organized by Apart Research in partnership with PIBBSS (Physics and Intelligence-Based Interdisciplinary Safety Studies).
Paper Club: When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
This is part two of our two-part series examining Chain-of-Thought reasoning in AI safety.
Intro to AI Safety
Curious about the risks and responsibilities that come with rapidly advancing AI technology?
Paper Club: "Chain-of-Thought Is Not Explainability"
This is part one of a two-part series examining the role of Chain-of-Thought (CoT) reasoning in AI safety.
AI Safety Research Exchange
Join fellow AI safety researchers for a collaborative gathering focused on sharing current work and exploring new opportunities.
Paper Club: A Moore's Law for AI Capabilities
Technical Note: This event is intended for participants with a technical background.
Paper Club: Chain-of-Thought Monitoring for Reward Hacking
Technical Note: This event is intended for participants with a technical background.
SASH X Lorong AI: Neural Networking (AI Safety)
Drop by for an evening of casual networking and conversations.
Paper Club: Safety Alignment Should Be Made More Than Just A Few Tokens Deep
Technical Note: This event is intended for participants with a technical background.
AI Safety Networking Social
We're pleased to invite you to attend a AI Safety networking social co-hosted by Concordia AI, FAR.AI, the Safe AI Forum, and Singapore AI Safety Hub.
Paper Club: Looking inside Claude’s “Brain”
Join us as we explore 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...
AI Control Hackathon 2025
As AI systems become more capable and autonomous, can we ensure that the control mechanisms around these systems remain robust?
Paper Club: AI Control — Safety Beyond Alignment
How can we ensure AI systems remain safe even when they might actively try to bypass the safety measures we put in place?
AI Safety: Can incomplete preferences keep artificial agents shutdownable?
Speaker Bio:
International AI Governance: Key Challenges and Solutions
International AI Governance: Key Challenges and Solutions
Singapore AI Safety Hub Launch Party
The Singapore AI Safety Hub (SASH) is a newly launched co-working, events and community space for people working on AI safety.
