BASE PAPER Reading Vol 9

​Paper of the Week: International AI Safety Report: Second Key Update: Technical Safeguards and Risk Management, AISI

​"This Key Update examines developments in technical approaches to general-purpose AI risk management, from training models to refuse harmful requests to watermarking AI-generated content. Since the publication of the 2025 International AI Safety Report, the number of companies publishing Frontier AI Safety Frameworks has more than doubled, and researchers have refined techniques for training safer models and detecting AI-generated content. However, significant gaps remain: sophisticated attackers can often bypass current defenses, and the real-world effectiveness of many safeguards is uncertain."

​​🌍 Black in AI Safety and Ethics (BASE) – Paper Reading on AI Safety and Governance Overview

​​​​​​We’re coming together to read, learn, and connect through ideas that shape the future of AI. During the paper reading, we will explore a research paper on AI safety and governance, taking the time to unpack key ideas and reflect on their implications for the responsible and inclusive development of AI.

​​​​​​The paper reading creates a space for Black people to learn, connect, and grow together in conversations about AI safety and ethics, while welcoming everyone who wants to learn alongside the community. You don't need to be an expert; you need to be open, curious, and ready to explore together.

Please come having read the paper and prepared to share.

​​​​​​🔍 What We Will Explore

​​​​​​💡 Understanding the ideas
We will read the selected paper together, highlighting what stands out, and discuss how these ideas apply to real-world contexts.

​​​​​​🌐 Sharing perspectives
We will exchange thoughts and reflections that help us better understand the challenges and opportunities of AI governance.

​​​​​​🤝 Learning in community
This is a space for shared learning, curiosity, and growth, where you can think deeply and connect through meaningful discussions.

​​​​​​🎙️ Moderated by

​​​​​​Abigail Y and Dwight Turner

​​​​​​✳️ About BASE

​​​​​​Black in AI Safety and Ethics (BASE) is a community created to make space for Black people in conversations about artificial intelligence, safety, and social responsibility. BASE encourages learning, mentorship, and collaboration while welcoming everyone who shares the goal of a more thoughtful and inclusive AI future.

​​​​​​Join us to read, reflect, and learn together.

Paper: International AI Safety Report: Second Key Update: Technical Safeguards and Risk Management