Policy work
We aim to improve AI governance over civilian applications, autonomous weapons and in nuclear launch.
Introduction
Improving the governance of transformative technologies
The policy team at FLI works to improve national and international governance of AI. FLI has spearheaded numerous efforts to this end.
In 2017 we created the influential Asilomar AI principles, a set of governance principles signed by thousands of leading minds in AI research and industry. More recently, our 2023 open letter caused a global debate on the rightful place of AI in our societies. FLI has given testimony at the U.S. Congress, the European Parliament, and other key jurisdictions.
In the civilian domain, we advise policymakers on how to best govern advanced AI systems. In the military domain, we advocate for a treaty on autonomous weapons at the United Nations and inform policymakers about the risks of incorporating AI systems into nuclear launch.
Our work
Policy projects
Combatting Deepfakes
2024 is rapidly turning into the Year of Fake. As part of a growing coalition of concerned organizations, FLI is calling on lawmakers to take meaningful steps to disrupt the AI-driven deepfake supply chain.
AI Safety Summits
Governments are increasingly cooperating to ensure AI Safety. FLI supports and encourages these efforts.
Developing possible AI rules for the US
Our US policy team advises policymakers in Congress and Statehouses on how to ensure that AI systems are safe and beneficial.
Engaging with the AI Executive Order
We provide formal input to agencies across the US federal government, including technical and policy expertise on a wide range of issues such as export controls, hardware governance, standard setting, procurement, and more.
AI Convergence: Risks at the Intersection of AI and Nuclear, Biological and Cyber Threats
The dual-use nature of AI systems can amplify the dual-use nature of other technologies—this is known as AI convergence. We provide policy expertise to policymakers in the United States in three key convergence areas: biological, nuclear, and cyber.
Strengthening the European AI Act
Our key recommendations include broadening the Act’s scope to regulate general purpose systems and extending the definition of prohibited manipulation to include any type of manipulatory technique, and manipulation that causes societal harm.
Educating about Lethal Autonomous Weapons
Military AI applications are rapidly expanding. We develop educational materials about how certain narrow classes of AI-powered weapons can harm national security and destabilize civilization, notably weapons where kill decisions are fully delegated to algorithms.
Global AI governance at the UN
Our involvement with the UN's work spans several years and initiatives, including the Roadmap for Digital Cooperation and the Global Digital Compact (GDC).
All our work
Our content
Latest policy papers
Turning Vision into Action: Implementing the Senate AI Roadmap
June 2024
Recommended Amendments to Legislative Proposals on Deepfakes
May 2024
FLI Response to OMB: Request for Information on Responsible Procurement of Artificial Intelligence in Government
April 2024
Competition in Generative AI: Future of Life Institute’s Feedback to the European Commission’s Consultation
March 2024
Load more
All Documents
Geographical Focus
Where you can find us
We are a hybrid organisation. Most of our policy work takes place in the US (D.C. and California), the EU (Brussels) and at the UN (New York and Geneva).
United States
In the US, FLI participates in the US AI Safety Institute consortium and promotes AI legislation at state and federal levels.
European Union
In Europe, our focus is on strong EU AI Act implementation and encouraging European states to support a treaty on autonomous weapons.
United Nations
At the UN, FLI advocates for a treaty on autonomous weapons and a new international agency to govern AI.
Key partners
Achievements
Some of the things we have achieved
Developed the AI Asilomar Principles
In 2017, FLI coordinated the development of the Asilomar AI Principles, one of the earliest and most influential sets of AI governance principles.
View the principles
AI recommendation in the UN digital cooperation roadmap
Our recommendations (3C) on the global governance of AI technologies were adopted in the UN Secretary-General's digital cooperation roadmap.
View the roadmap
Max Tegmark's testimony to the EU parliament
Our founder and board member Max Tegmark presented a testimony on the regulation of general-purpose AI systems in the EU parliament.
Watch the testimony
Our content
Featured posts
Here is a selection of posts relating to our policy work:
Artist Rights Alliance, Annie Lennox Speak Out with Ban Deepfakes Campaign
Lennox states: "we need to hold the tech companies whose AI models enable this harm accountable."
2 August, 2024
Poll Shows Broad Popularity of CA SB1047 to Regulate AI
A new poll from the AI Policy Institute shows broad and overwhelming support for SB1047, a bill to evaluate the risk of catastrophic harm posed by AI models.
23 July, 2024
Evaluation of Deepfakes Proposals in Congress
How do the leading US legislative proposals on the issue of deepfakes compare?
31 May, 2024
Disrupting the Deepfake Pipeline in Europe
Leveraging corporate criminal liability under the Violence Against Women Directive to safeguard against pornographic deepfake exploitation.
22 February, 2024
Exploration of secure hardware solutions for safe AI deployment
This collaboration between the Future of Life Institute and Mithril Security explores hardware-backed AI governance tools for transparency, traceability, and confidentiality.
30 November, 2023
Protect the EU AI Act
A last-ditch assault on the EU AI Act threatens to jeopardise one of the legislation's most important functions: preventing our most powerful AI models from causing widespread harm to society.
22 November, 2023
Miles Apart: Comparing key AI Act proposals
Our analysis shows that the recent non-paper drafted by Italy, France, and Germany largely fails to provide any provisions on foundation models or general purpose AI systems, and offers much less oversight and enforcement than the existing alternatives.
21 November, 2023
Can we rely on information sharing?
We have examined the Terms of Use of major General-Purpose AI system developers and found that they fail to provide assurances about the quality, reliability, and accuracy of their products or services.
26 October, 2023
Our content
Contact us
Let's put you in touch with the right person.
We do our best to respond to all incoming queries within three business days. Our team is spread across the globe, so please be considerate and remember that the person you are contacting may not be in your timezone.
Please direct media requests and speaking invitations for Max Tegmark to press@futureoflife.org. All other inquiries can be sent to contact@futureoflife.org.