[Lobang] IMDA TSS

(Disclaimer: Not sponsored or directly affiliated to organisation, adding this here since it’s relevant to Responsible AI/AI Safety)

As AI systems and frontier models become increasingly interactive and deeply woven into our daily lives, a critical question emerges: How do we keep human-AI interactions genuinely safe?

Join us for our next Technical Sharing Session to find out.

On 30 July 2026, from 2:30pm to 5:00pm at IMDA's Office (10 Pasir Panjang Road, Level 4 Communal Cafe), we are bringing together local and global experts from IMDA, FAR.AI and the University of Southern California, for a technical deep dive into Safer Human-AI Interactions!

Here’s a quick teaser of what we’ll be covering:

Human-AI Interactions: Navigating unique risks brought upon by highly interactive and emotional AI systems in use cases such as AI for companionship.

Frontier Red-Teaming: Stress-testing frontier models to identify hidden gaps within top-tier model safeguards.

Advanced AI Risks: Exploring the complex mechanics behind the risks of persuasion and psychological steering behaviors posed by LLMs.

Link:

https://form.gov.sg/6a277d197abb59ae43966e7a