International Dialogues on AI Safety

Western and Chinese scientists: AI safety a “global public good”, global cooperation urgently needed.

Leading global artificial intelligence (AI) scientists gathered in Venice in September where they issued a call urging governments and researchers to collaborate to address AI risks. Computer scientists including Turing Award winners Yoshua Bengio and Andrew Yao, as well as UC Berkeley professor Stuart Russell, OBE and Zhang Ya-Qin, Chair Professor at Tsinghua University, convened for the third in a series of International Dialogues on AI Safety (IDAIS), hosted by the Safe AI Forum (SAIF) in collaboration with the Berggruen Institute.

The event took place over three days at the Casa dei Tre Oci in Venice and focused on safety efforts around so-called artificial general intelligence. The first day involved a series of discussions centered around the nature of AI risks and the variety of strategies required to counter them. Session topics included early warning thresholds, AI Safety Institutes, verification and international governance mechanisms.

These discussions became the basis of a consensus statement signed by the scientists, centered around the idea that AI safety is a “global public good”, suggesting that states carve out AI safety as a cooperative area of academic and technical activity. The statement calls for three areas of policy and research. First, they advocate for “Emergency Preparedness Agreements and Institutions”, a set of global authorities and agreements which could coordinate on AI risk. Then, they suggest developing “Safety Assurance Frameworks”, a more comprehensive set of safety guarantees for advanced AI systems. Finally, they advocate for more AI Safety funding and research into verification systems to ensure that safety claims made by developers or states are trustworthy. The full statement can be read below.

On the second day, scientists were joined by a group of policymakers, former President of Ireland Mary Robinson and other experts. The scientists emphasized the urgency of employing these proposals given the rapid pace of AI development. The statement was presented directly to the policymakers, and the group strategized about how the international community may work together to accomplish these goals.

In the Inaugural IDAIS, International Scientists Call for Global Action on AI Safety.

Ahead of the highly anticipated AI Safety Summit, leading AI scientists from the US, the PRC, the UK and other countries agreed on the importance of global cooperation and jointly called for research and policies to prevent unacceptable risks from advanced AI.

Prominent scientists gathered from the USA, the PRC, the UK, Europe, and Canada for the first International Dialogues on AI Safety. The meeting was convened by Turing Award winners Yoshua Bengio and Andrew Yao, UC Berkeley professor Stuart Russell, OBE, and founding Dean of the Tsinghua Institute for AI Industry Research Ya-Qin Zhang. The event took place at Ditchley Park near Oxford. Attendees worked to build a shared understanding of risks from advanced AI systems, inform intergovernmental processes, and lay the foundations for further cooperation to prevent worst-case outcomes from AI development.