RESI is a research community spanning technical, legal, and economic expertise
Superintelligence safety has many aspects, and no single discipline sees the whole picture. Drawing on the concentration of talent in the Cambridge area, RESI brings together researchers in computer science and other fields relevant to AI safety, including mathematics, economics and law. Working groups, seminars, and an active visitor program connect senior and early-career scholars to collaborate on shared research problems.
How we work
Research excellence and independence
RESI combines research excellence with independence of industry and profit incentives.
RESI aims to recreate the conditions which led to big ideas in the past, amplified by AI tools, with an open, mission-first culture that values sharing over being first to publish.
Our sole goal is the responsible and safe use of AI to the betterment of humanity.
Shaping AI systems and policy
Our long-term goal is for safe by design approaches to be adopted in advanced AI systems and for research to inform policy and regulation.
RESI designs with practical constraints in mind and tests promising constructions in real systems. Where implementation requires resources beyond RESI’s capacity, we will share proofs of concept so that frontier AI developers can evaluate and adopt them.
What success will look like
The ultimate success would be new safe by design approaches adopted in frontier AI systems.
Progress includes rigorous definitions of safety objectives, maps of what is and is not achievable under explicit assumptions, new mechanisms with useful guarantees, results on how guarantees compose, and working demonstrations in real systems.
Success also means influencing policy and regulation in ways that support human flourishing.
FAQ
What do you mean by superintelligence?
Superintelligence means systems that greatly exceed individual humans, and potentially expert teams, across a broad range of cognitive tasks.
Does a proof make an entire AI system safe?
No. A proof concerns a specified property in a specified model, under stated assumptions. Whether those assumptions describe a deployed system, and whether the property captures what people need, are separate questions.
Does this replace testing or alignment research?
No. Formal analysis, empirical evaluation, and work on alignment address different parts of the problem. A useful design needs to be checked both against its specification and against the conditions in which it will operate.
Why an independent institute?
RESI combines academic independence with sustained focus on the foundations of AI safety. It brings researchers together across fields, with an open, mission-first culture.
How can research shape AI systems and policy?
RESI designs with practical constraints in mind and tests promising constructions in real systems. We will share proofs of concept so that frontier AI developers can evaluate and adopt them. Success also means influencing policy and regulation in ways that support human flourishing.