Presenter Roland Pihlakas Roland Pihlakas, MSc in psychology, is an experienced AI software engineer who has been working on multi-objective value problems for almost 20 years, and has followed discussions on AI Safety since 2006. His thesis topic was about modelling of innate learning and planning mechanisms, which eventually form a foundation for culturally acquired… Continue reading R. Pihlakas | Biologically and Economically Aligned Multi-objective Multi-agent AI Safety Benchmarks
Presenter Marc Carauleanu Marc Carauleanu is an AI Safety Researcher at AE Studio. They are leading a team investigating a neglected AI Safety proposal that is focusing on self-other overlap: the AI model having similar internal representations when it reasons about others to when it reasons about itself. This agenda was heavily inspired by scientific… Continue reading Marc Carauleanu | Self-Other Overlap: A Neglected Path to Existential Safety
Presenter Stuart Armstrong Prior to co-founding Aligned AI, Dr. Stuart Armstrongspent a decade at the Future of Humanity Institute at Oxford University doing deep analysis on the biggest threats confronting humanity including nuclear threats, pandemics, human extinction, space colonisation, and – above all else – AI. Focusing on the power and risk of AI long… Continue reading Stuart Armstrong | Why AI’s Fail
Presenter Scott Emmons Scott Emmons is a PhD student in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. Advised by Stuart Russell, he works with the Center for Human-Compatible AI to help ensure that increasingly powerful artificial intelligence systems are robustly beneficial. He is grateful for the past support… Continue reading Scott Emmons | When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Lea
Presenter Evan Miyazono Evan leads Atlas Computing, a nonprofit mapping and prototyping ways to achieve human governance and provable safety of advanced AI. He previously created and led a venture studio focused on public goods funding mechanisms, a metascience team, and a research grants program at Protocol Labs (the company that initially created IPFS and… Continue reading Evan Miyazono | Formally Scalable AI Oversight Through Specifications
Presenter Aslan Satary Dizaji Aslan is a scientist and entrepreneur, has cofounded AutocurriculaLab and Neuro-Inspired Vision in 2022, and currently working toward building artificial systems simulating human behaviors. Summary: Artificial intelligence can be used to simulate social phenomena. In this respect, a branch of artificial intelligence, called multi-agent reinforcement learning, is one of the most… Continue reading Aslan Satary Dizaji | Evolution of Communication Under Libertarian and Utilitarian Governing Systems
Presenter James Petrie Technical AI Governance Researcher In an age where reliable computer security is critical, Foresight Institute proudly announces Covid Watch as the winner of the inaugural 2023 Norm Hardy Prize for its significant contribution to the field of usable security. This prize celebrates work building upon the vision of the late computer scientist,… Continue reading James Petrie | Covid Watch: Norm Hardy Prize Winner 2023
Presenter DC, Worldcoin Foundation DC is a research engineer at the Worldcoin Foundation where he focuses on advancing the state of the art of privacy preserving digital identity, programmable cryptography and blockchain scalability. Summary: An introduction to Zero Knowledge Machine Learning. In the age of AI we need to have ways of verifying data provenance… Continue reading DC | An Overview of Zero Knowledge Machine Learning
Presenter Christian Schroeder de Witt Christian is a researcher in foundational AI, information security, and AI safety, with a current focus on the limits of undetectability. Lately, he has been busy pioneering the field of Multi-Agent Security (masec.ai), which aims to overcome the safety and security issues inherent in contemporary approaches to multi-agent AI. His… Continue reading C. Schroeder de Witt | Secret Collusion Among Generative AI Agents: Toward Multi-Agent Security
