Loading results...
Showing 3951-4000 of 4523 results
Postdoctoral fellow in the Algorithmic Alignment Group and SERC at MIT whose research on minds, machines, and morality draws on virtue ethics, game theory, and computational complexity to inform the design of AI systems that better capture human values and thought.
No summary available yet.
LLMs scale language, not method. HP turns hypothesis-driven papers into machine-readable maps of variables, controls, stats, and findings for researchers & AI.
Head of Policy at the AI Policy Network and co-founder and former Chief Strategy Officer of the Institute for AI Policy and Strategy (IAPS); previously co-founded Rethink Priorities and worked as a data scientist, and is known as a top forecaster involved in AI and policy-focused forecasting competitions.
No summary available yet.
Member of Technical Staff at Sage’s AI Digest and AI Village projects, working on interactive AI demos and explainers and publicly writing about AI capabilities and agent behavior.
CEA builds and supports the global effective altruism community through conferences, online platforms, local group support, grantmaking, and community health programs, helping people use evidence and reason to address the world's most pressing problems.
Researcher at Cavendish Labs and PhD student in chemistry at the University of California, Berkeley, with previous undergraduate study in chemistry at Brown University.
3-month salary to set up a distillation course helping new AI safety theory researchers to distill papers
Senior researcher with MIT FutureTech and The University of Queensland who provides methodological expertise and strategic and technical advice for the AI Risk Index, drawing on experience with systematic reviews, Delphi studies, and meta‑analyses.
No summary available yet.
No summary available yet.
Studying extensions of the AIXI model to reflective agents to understand the behavior of self modifying A.G.I
No summary available yet.
No summary available yet.
Allow Berkeley PhD student to devote more time and focus to AI safety research and mentorship.
No summary available yet.
No summary available yet.
No summary available yet.
No summary available yet.
Funding for 6-Month AI strategy/policy research stay at CSER with Seán Ó hÉigeartaigh & Matthew Gentzel
No summary available yet.
Stop AGI is a project and website launched by Andrea Miotti in April 2023 to communicate the extinction risks of artificial general intelligence to the public and propose policy solutions to prevent its development.
AI researcher and writer who co-authored “The Intelligence Curse” essay series and previously researched AI governance and economics at BlueDot Impact, served on the leadership team at Encode, and studied history and politics at the University of Oxford.
WhiteBox Research: 1.9 FTE for 9 months to pilot a training program in Manila focused on Mechanistic Interpretability
No summary available yet.
Esben Kran is the founder of Apart Research, which he started after leaving graduate school in his early twenties, and co-founder of the AI safety venture studio Seldon; he focuses on scaling AI safety research via hackathons, fellowships, and award-winning benchmarks and tools for evaluating advanced AI systems.
McKenna Meyer is Chief of Staff at FutureSearch. She holds a BA from the University of Michigan and previously worked on talent acquisition strategy at Google, where she led program management for Google’s internal prediction market run by the Behavioral Economics team.
No summary available yet.
Aengus Lynch is an AI safety researcher who recently completed his PhD in Artificial Intelligence at University College London (UCL), supervised by Prof. Ricardo Silva, and holds an MSci in Mathematics (First Class Honours) from UCL. He was a MATS 5.0 scholar mentored by Stephen Casper, where he worked on LLM unlearning and adversarial robustness, including latent adversarial training. His research focuses on AI alignment, mechanistic interpretability, adversarial robustness, and agentic misalignment. He is a co-author of "Agentic Misalignment: How LLMs Could be Insider Threats" (2025), a widely covered paper demonstrating that frontier AI models from all major labs engage in blackmail and deception when pursuing goals autonomously. Since August 2024 he has worked as a contract researcher with Anthropic and is a founding member of Watertight AI, a company building reward hacking monitors for reinforcement learning training. He has also contributed to research at FAR.AI and the Redwood Research REMIX program.
Formalizing the "Safety Ceiling": An Agda-Verified Impossibility Theorem for AI Alignment
No summary available yet.
No summary available yet.
Researcher at METR (Model Evaluation and Threat Research) and Program Associate at the AI Risk Mitigation Fund; previously worked on mechanistic interpretability and adversarial training at Redwood Research and is a PhD student in AI at UC Berkeley’s Center for Human-Compatible AI.
Abhay Sheshadri is an AI safety researcher currently serving as a Research Fellow at Anthropic, which he joined in 2025 after completing his undergraduate degree in Computer Science at Georgia Institute of Technology (2021–2025). He was previously a researcher at MATS (2023–2025), participating in the MATS 5.0 program, and interned at the Center for Human-Compatible AI (CHAI) at UC Berkeley in 2024. His research focuses on mechanistic interpretability, alignment auditing, and robustness of large language models. Key contributions include co-authoring work on Latent Adversarial Training to improve LLM robustness against jailbreaks and backdoors, leading the Anthropic Fellows research that produced AuditBench (a benchmark of 56 LLMs with implanted hidden behaviors for evaluating alignment auditing techniques), co-authoring a study on alignment faking across 25 frontier models, and publishing mechanistic interpretability work at ACL 2024 and ICML 2025. He posts on the AI Alignment Forum under the handle abhayesian.
No summary available yet.
No summary available yet.
Jamie Joyce is the founder and Executive Director of the Society Library, a nonprofit that builds structured knowledge databases of media about debates on complex social issues to improve humanity’s relationship with information online. Her projects include the Great American Debate on climate change, the Internet Government, and COVIDConvo. She previously worked in international sustainable development, overseeing projects in more than 20 countries and representing an NGO at the United Nations, and she serves on the board of Wikitongues.
Research Director (fagsjef) at Langsikt, responsible for the think tank’s analysis and policy development. He is a political scientist and philosopher who has long worked at the intersection of economics, politics and ethics, leads a research project on the valuation of animals at the University of Oslo, and has taught AI ethics at Harvard University, the University of Oxford and the University of Oslo. He is a former commentator in Dagbladet and the author of books on topics such as social democracy.
Samuel Nellessen is an AI safety researcher based in Berlin, Germany, currently resident at the Foresight Node in Berlin with independent research grant support. He studied Philosophy, Neuroscience and Cognition at a university in Magdeburg before transitioning to a degree in Artificial Intelligence at Radboud University in Nijmegen, Netherlands. He was a 2024 Foresight Neurotech Fellow, where he worked with Roshan Cools on Bayesian models of controllability in clinical depression. He completed the ARENA v5 bootcamp and has focused his research on mechanistic interpretability, automated red-teaming, and building systems that autonomously identify failure modes in large language models, including jailbreaking frontier models using reinforcement learning. He received a Long-Term Future Fund grant to self-study machine learning and explore applications of neuroscience and cognitive science to AGI safety, reflecting his interdisciplinary background bridging natural and artificial intelligence.
No summary available yet.
Corn
No summary available yet.
No summary available yet.
No summary available yet.
Meta level adversarial evaluation of debate (scalable oversight technique) on simple math problems (MATS 5.0 project)
Co-founder and research lead at Simplex, with deep expertise in the physics of information and the fundamental limits of learning and prediction. He holds a PhD in theoretical physics and an MS in electrical and computer engineering from UC Davis, previously spent five years as a Research Fellow at Nanyang Technological University in Singapore, co-founded the Beyond Institute for Theoretical Science (BITS), served as a Senior Fellow at UCLA’s Mathematics of Intelligences program at IPAM, and has been both a MATS scholar and mentor while co-leading the growing Simplex team.
Research project through the Legal Priorities Project, to understand and advise legal practitioners on the long-term challenges of AI in the judiciary
