Guillaume Corlouer is an independent AI safety researcher based in Brighton, England. He holds a PhD from the University of Sussex (Sackler Center for Consciousness Science), where he studied information flow in ECoG time series during visual perception under the supervision of Lionel Barnett and Anil Seth, with prior training in mathematics at the University of Paris-Sud. His AI safety work centers on mechanistic interpretability, applying information-theoretic and complex-systems methods to discover latent variables from neural network activations. He was a fellow in the 2023 PIBBSS program, investigating stochastic gradient descent on singular models in the context of Singular Learning Theory, and subsequently a PIBBSS research affiliate, during which he co-authored an information-theoretic study of lying in LLMs presented at the ICML 2024 Workshop on LLMs and Cognition. He also participated in AI Safety Camp 8 (2023), where his team produced the paper "Linearly Structured World Representations in Maze-Solving Transformers," demonstrating that transformers trained on maze-solving learn linear representations of maze structure.

No summary available yet.

Data scientist with a BSc in Cognitive Science, an MSc in Computer Science, and a PhD in player modeling in video games, with past research at the MIT Media Lab and the European Space Agency; currently a Member of Technical Staff at AI Digest working on the AI Village and related projects.

No summary available yet.

No summary available yet.

Andrew Gritsevskiy is an AI safety researcher and entrepreneur based in San Francisco, California. He co-founded Contramont Research, a nonprofit AI safety lab focused on cryptographic model organisms and understanding where safety and security methods break, and co-founded Cavendish Labs, a Vermont-based research institute addressing AI safety and pandemic prevention. He was a PhD student in computer science at the University of Wisconsin-Madison before leaving to co-found RunRL (Y Combinator Spring 2025), a reinforcement learning platform. He participated in the MATS (ML Alignment Theory Scholars) program and has been affiliated with FAR.AI. His most notable research contribution is the paper "Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits" (NeurIPS 2024), which demonstrated backdoors in transformer models that cannot be triggered or detected even with full white-box access, fundamentally challenging the efficacy of pre-deployment safety evaluations. He also won Third Prize in the Inverse Scaling Prize competition for work on prompt injection.

Liz Ibarra is the Co‑Working Space Manager at FAR.AI, responsible for workplace experience strategy and building the systems, culture, and environments that enable teams to thrive. She designs operational frameworks across events, space planning, and employee engagement to ensure smooth operations and a strong sense of community. Previously, she supported workplace experience programs at OpenAI and Google and serves as a Co‑Event Director for the Children’s Tumor Foundation, helping lead large‑scale fundraising events, volunteer operations, and donor engagement. She is pursuing an MBA focused on workplace leadership and organizational psychology.

Kavita Bhatia is Chief Operating Officer of the IndiaAI Mission and a senior official at the Ministry of Electronics and Information Technology, serving as Scientist G and Group Coordinator for AI and Emerging Technologies in the Government of India.

No summary available yet.

Nikhil Mulani is an AI policy and technology researcher who completed an executive branch fellowship at the U.S. Cybersecurity and Infrastructure Security Agency, working on frontier AI policy and security. He has collaborated with the Centre for Long-Term Resilience on projects to inform UK AI regulation and international policy, and was a Winter Fellow at the Centre for the Governance of AI, where he developed proposals for information-sharing between leading AI labs and the UK Office for AI. Before moving into policy, he spent over six years as a product manager building machine-learning software and as a consultant advising commercial and government clients on technology strategy. He holds an MBA from the Wharton School and a BA in Classics from Harvard University.

No summary available yet.

Gergely Szucs is a mathematician who transitioned into AI safety research. He received his PhD in Mathematics from Stanford University in 2018, where his dissertation focused on the equivariant cobordism category under advisor Søren Galatius. After graduating he worked as a software engineer at Google before moving into AI alignment research. He spent approximately two years working with Vanessa Kosoy on the Learning Theoretic Agenda as part of ALTER-US, a project supporting learning-theoretic approaches to AI safety. His research focused on Infra-Bayesian approaches for mathematical AI safety, including work on infrabayesian physicalism. He co-organized a recorded lecture series on statistical learning theory for alignment researchers and prepared course materials for an AI safety workshop in summer 2024. He received a grant from the Long-Term Future Fund to develop an overview of the current state of AI alignment research and begin contributing to the field. As of mid-2025, he departed ALTER to pursue interests outside of mathematics and AI alignment.

No summary available yet.

Julian Guidote is a Canadian law graduate and aspiring AI liability lawyer based in Quebec, Canada. He holds a B.A.Sc., BCL, and JD from McGill University, and is a Certified Information Privacy Professional - Canada (CIPP/C). After nearly a decade supporting vulnerable communities, he pivoted toward tech law and AI governance, spending approximately eight months post-graduation upskilling in policy, privacy, and AI alignment. He has completed BlueDot Impact courses in AI Alignment, Transformative AI, and AI Governance, and has worked as a policy analyst for the Government of Canada. He received a Long-Term Future Fund grant with co-researcher Ben Chancey to research and publish a policy proposal on Mandatory AI Safety 'Red Bonds,' a novel regulatory mechanism for AI safety compliance. He has been active in EA circles, presenting on the intersection of law and effective altruism at the 2022 EAGT Unconference.

No summary available yet.

No summary available yet.

No summary available yet.

No summary available yet.

No summary available yet.

No summary available yet.

Rusheb Shah is a Research Engineer at Apollo Research, an AI safety organization focused on evaluating and auditing high-risk failure modes in frontier AI systems. He holds a Master's degree in Materials Science from the University of Oxford and completed the Alignment Research Engineer Accelerator (ARENA) program to transition into technical AI safety work. Before joining Apollo Research in December 2023, he briefly worked at OpenAI and previously held software engineering roles at R3, Brainlabs, and Amazon Web Services. His research at Apollo Research focuses on LLM evaluations, including co-authoring work on evaluations-based safety cases for AI scheming and research on scalable black-box jailbreaks via persona modulation. He also contributed to the mechanistic interpretability library TransformerLens by adding BERT support and won first prize at the ARENA Interpretability Hackathon for work on circuit discovery algorithms.

Jeremy Gillen is an independent AI alignment researcher based in Berkeley, California, working primarily on agent foundations and the ontology identification problem. He holds an undergraduate degree in Computer Science and Neuroscience with a thesis on statistical learning theory. He participated in the SERI MATS (ML Alignment Theory Scholars Program) cohort 2 under mentor John Wentworth, where he co-authored "Finding Goals in the World Model" — a proposal for aligning model-based RL systems by identifying human values in a world model and using inverse reinforcement learning to guide the policy. Following MATS, he received a Long-Term Future Fund grant to continue independent research on alignment problems in model-based RL. He subsequently joined Vivek Chan's team at MIRI (Machine Intelligence Research Institute) before returning to independent research. His current work focuses on the ontology identification problem and related natural abstractions research, with recent co-authored work on condensation and natural latents. He is an active contributor to LessWrong and the AI Alignment Forum, and has participated in public debates on AI corrigibility.

No summary available yet.

No summary available yet.

James Norris is the Founder and Executive Director of the Center for Existential Safety and the Founder and CEO of Upgradable and Survival Sanctuaries, with over 20 years of experience in social entrepreneurship, behavior change, and systems innovation. He has co-founded or helped build 27 organizations, including the international conference for the effective altruism movement.

No summary available yet.

No summary available yet.

No summary available yet.

Samuel Hammond is director of Artificial Intelligence Policy and chief economist at the Foundation for American Innovation, where his research focuses on innovation policy, artificial intelligence, and the institutional impact of emerging technologies. He previously served as director of social policy at the Niskanen Center, worked as an economist for the Government of Canada, and was a graduate research fellow at the Mercatus Center.

No summary available yet.

Bryce Hidysmith was previously a designer and strategist for the hedge fund Numerai and writes essays at hidysmith.com.

Executive Director of CEEALAR, where he is leading its evolution into a high-impact EA hub. He brings experience in R&D leadership at global organisations, the startup ecosystem, education, customer service and military service, and focuses on creating communities where talented people can do impactful work.

No summary available yet.

No summary available yet.

Early contributor to the AI Safety Awareness Project remembered in its "In Memoriam" section. He previously played online poker professionally for five years, spent four months at the Recurse Center focusing on AI and reinforcement learning, received a grant from the Machine Intelligence Research Institute (MIRI) to upskill in machine learning, and participated in AI Safety Camp as both participant and organizer. He later founded Poker Camp, a nonprofit that uses poker to teach probability, AI, and decision-making under uncertainty. He held a B.S. in Electrical Engineering from Northwestern University and an M.Sc. in Electrical Engineering from the Technion – Israel Institute of Technology.

No summary available yet.

No summary available yet.

No summary available yet.

José Luis Cordeiro is a Venezuelan-Spanish engineer, economist, and futurist who chairs The Millennium Project’s Venezuela Node and serves on its Board of Directors. He founded the World Future Society Venezuela, previously directed the Venezuela Chapter of the Club of Rome, holds degrees from Universidad Simón Bolívar, INSEAD, and MIT, and has authored more than ten books, including the bestseller La muerte de la muerte on radical life extension.

Eric Easley is an AI safety researcher and machine learning researcher affiliated with the ML Alignment & Theory Scholars (MATS) program, based in San Francisco, CA. He holds a Bachelor's degree in Physics and Economics from The Ohio State University. Prior to focusing on AI alignment research, he gained software engineering experience at companies including PullRequest and Coursera. He received a grant from the Long-Term Future Fund (LTFF) for a 6-month research stipend focused on removing conditional bad behaviors from large language models via a learned latent space intervention, exploring how latent representations in LLMs can be used to durably eliminate undesirable model behaviors rather than merely suppress them. His GitHub profile (username: pseudonom) shows a background in functional programming, particularly Haskell.

Liam Carroll is a Researcher in AI Safety based in Melbourne, Australia, jointly affiliated with Timaeus and the Gradient Institute. He holds a Master of Mathematics from the University of Melbourne (2021), where his thesis on Phase Transitions in Neural Networks was supervised by Dr. Daniel Murfet and Dr. Thomas Quella, and a Bachelor of Science in Applied Mathematics alongside a Diploma of Music in Clarinet Performance. Prior to his current role, he was an independent researcher in Developmental Interpretability (2023-2024), funded by a Lightspeed Grant, during which he co-authored papers on the stagewise development of neural networks using Singular Learning Theory. He received a Long-Term Future Fund grant to write a LessWrong sequence called Distilling SLT, which translates the technical foundations of Watanabe's Singular Learning Theory into accessible form for the AI safety community. Carroll also organized the inaugural Australian AI Safety Forum in Sydney in November 2024, and brings a distinctive background as a wilderness hiking guide in Tasmania and a music educator.

Design and product specialist working at Atlas Computing.

Adam Shimi is a French AI safety researcher currently working as a Policy Researcher at ControlAI, a non-profit focused on preventing the development of unsafe superintelligence, based in London. He completed his PhD in theoretical computer science at the Université de Toulouse (IRIT) in 2020, where his dissertation focused on distributed computing and the Heard-Of model, and holds an engineering degree in Computer Science and Applied Mathematics from ENSEEIHT (2014-2017). Prior to ControlAI, he was a co-founder and early staff member at Conjecture, an AI alignment research startup, where he also founded Refine, a three-month incubator for conceptual alignment researchers to develop new research directions. He has conducted independent AI alignment research with support from the Long-Term Future Fund and is an active contributor to the Alignment Forum and LessWrong, with over 124 posts and 875 comments. His research interests span epistemology of alignment, agent foundations, goal-directedness, and the methodology of AI safety research, and he blogs at For Methods (formethods.substack.com).

No summary available yet.

No summary available yet.

Romain Graux is a systems specialist and machine learning engineer at EPFL’s Computational Molecular Design Laboratory who writes about AI safety, deep learning, and software. Public profiles indicate that he works at EPFL in a systems specialist role, and event listings show him helping to host and organize AI safety events at EPFL, including the AI Horizons panel on the Swiss AI Initiative and earlier multi-agent safety hackathons.

Head of Global Partnerships at the Collective Intelligence Project and a global community organizer with experience building international coalitions, advising policymakers, and working on human rights, digital rights, education, public health, climate, and social movements across regions including Nepal, South Africa, India, Sri Lanka, the UK, and the US.

Co-founder and principal investigator of the Alignment of Complex Systems Research Group at Charles University’s Center for Theoretical Study, previously a research fellow at Oxford’s Future of Humanity Institute working on macrostrategy, AI alignment, and existential risk.

Chris Lakin is an independent AI safety researcher and writer based in San Francisco. He studied physics at Carnegie Mellon University and previously contributed to New Science, a metascience non-profit. His primary research focus is formalizing the concept of "boundaries" or "membranes" as a rigorous safety specification for AI systems, drawing on Markov blankets and connections to agent autonomy in psychology. He has written widely-read distillation posts on this topic for LessWrong and the Alignment Forum, and organized two workshops: the Conceptual Boundaries Workshop (February 2024, Austin) and the Mathematical Boundaries Workshop (April 2024, Berkeley area), bringing together researchers including David Dalrymple, Scott Garrabrant, and Andrew Critch. His work has been funded by the Long-Term Future Fund, the Foresight Institute, and a joint $40,000 ACX Grant (2024) with Evan Miyazono. He writes the "Locally Optimal" Substack newsletter (3,300+ subscribers) and maintains a project site at formalizingboundaries.ai.