Loading results...
Showing 3551-3600 of 3954 results
Clear filtersSoftware and AI safety researcher working on AI security via formal methods; Researcher at the Beneficial AI Foundation and author of the Substack newsletter 'Can We Secure AI With Formal Methods?'.
Showing 3551-3600 of 3954 results
Active filters: Type: Project, Individual
Clear filters to view everything →
Joshua Clymer is a technical AI safety researcher at Redwood Research, where he specializes in safety evaluation methodologies for advanced AI agents. Prior to Redwood Research, he researched AI threat models and developed evaluations for self-improvement capabilities at METR. He received a $1,500 Long-Term Future Fund grant for compute resources to develop an instruction-following generalization benchmark, which resulted in the GENIES (GENeralization analogIES) benchmark and a paper demonstrating that reward models do not learn to evaluate instruction-following by default and instead favor personas resembling internet text. He is also known for the Poser paper, which introduced a benchmark for detecting alignment-faking LLMs by manipulating model internals, achieving a 98% detection rate. Clymer co-authored a widely cited safety cases report and has contributed to work on AI control, scheming evaluations, and international agreement verification. He founded Dioptra, a volunteer research group building evals for AI safety, and was among the early signatories of the CAIS Statement on AI Risk. He is affiliated with the Cambridge Boston Alignment Initiative as a mentor.
No summary available yet.
Seeking short term grant to finance career transition
No summary available yet.
John Sherman is a Peabody and multi-Emmy Award–winning former investigative journalist based in Baltimore, founder of the nonprofit GuardRailNow and President of The AI Risk Network. He previously founded and led the video agency Storyfarm and serves as Director of Public Engagement at the Center for AI Safety, where he leads efforts to bring AI extinction risk into mainstream public consciousness through the For Humanity podcast, The AI Risk Network media properties, and related public-facing campaigns.
No summary available yet.
Tobias Eugene Alcock Newberry is a New Zealander based in England who serves as a director of Macrostrategy Research Initiative Limited, with his registered occupation listed as Chief of Staff.
No summary available yet.
Co-lead and research analyst at AI Standards Lab and Research Affiliate at the Oxford Martin AI Governance Initiative, working on threat models and risk pathways for advanced AI systems and on evaluating and improving AI safety standards; previously a reservoir engineer with over a decade of industry experience in the oil and gas sector.
Hi I'm Anthony, I currently focused on AI safety and governance as a progression of my work with startups and small businesses over the past 15 years.
Jen Ellis is a cybersecurity policy expert and founder of NextJenSecurity who serves as a Ransomware Task Force working group co‑chair with the Institute for Security and Technology, working to reduce cyber risk for digital citizens by fostering collaboration among security experts, technology providers, civil society, and governments.
No summary available yet.
Bookkeeper for the Berkeley Existential Risk Initiative and Managing Director of Oak Books Limited. She provides bookkeeping services to a range of clients, with a particular focus on nonprofit organizations, and first began working with BERI in 2019.
No summary available yet.
No summary available yet.
Summer Research Fellow in U.S. law and policy at LawAI whose work focuses on AI governance and how emerging legal technologies can support civic engagement, civil rights, and equitable access to justice. Previously worked on policy and strategic planning at the U.S. Department of Commerce under Secretary Gina Raimondo, served in the Biden–Harris White House, and held roles at the ACLU’s Justice Division, the Center for American Progress, and the National Women’s Law Center. She holds an A.B. from Princeton University’s School of Public and International Affairs and is pursuing a J.D. at Harvard Law School.
Sandra Joyce is a cybersecurity leader with over 25 years of intelligence experience who heads Google Threat Intelligence at Google Cloud and serves on the Ransomware Task Force Steering Committee convened by the Institute for Security and Technology, alongside other roles on national security and cyber policy advisory bodies.
Researcher at AI Standards Lab focusing on security, privacy, governance, and deep learning, and co-author of work on risk sources and risk management measures for general-purpose AI systems as well as other AI safety and evaluation research.
No summary available yet.
No summary available yet.
Griff Bohm is a co‑founder and General Partner at Juniper Ventures, bringing a background in behavioral psychology and growth leadership at AI-powered fundraising startup Momentum, where he has served in senior roles such as CRO and COO.
No summary available yet.
No summary available yet.
No summary available yet.
No summary available yet.
Media and communications professional focused on existential risk, who from 2015 to 2022 worked at the Future of Life Institute on conferences, open letters, grant programs and campaigns on AI safety, synthetic biology, and nuclear weapons risk, and who hosted the Future of Life Institute Podcast reaching millions of views on existential risk content.
French Center for AI Safety
Novel safety failure modes discovered across 7 LLM providers with 35,000+ controlled inference trials. Targeting NeurIPS 2026.
$5,000 USD to bring 16 vetted academics and policy leads to NZ's first AI Safety Conference, ensuring national representation and cross-sector collaboration
Open Welfare Alignment Evals for Frontier Models
4-month salary for finding and characterising provably hard cases for mechanistic anomaly detection
AI safety, communications, generalist
Deputy Managing Director at the ETH Zurich Foundation, with a focus on international partnerships and philanthropy to secure support for ETH Zurich.
No summary available yet.
General support for Alexander Turner and team research project - Writing new motivations into a policy network by understanding and controlling its internal decision-influences
Building early AI governance and safety systems focused on alignment, oversight and risk reduction before more capable AI arrives.
Independent Interdisciplinary Researcher Focus: Unified Geometric Physics, Systemic Bioenergetics, Computational Safety, Philosophy & Literature
A seasoned leader in AI startups, I'm now building Tech/ish to connect technologists with communities for beneficial AI.
No summary available yet.
Partner at Lightspeed Venture Partners focused on developer productivity tools, application infrastructure, and machine learning in the enterprise, where he backs technical founders including Goodfire.
Effective altruist interested in non-human welfare, longtermism, & moral circle expansion
No summary available yet.
Chris Dolman is an actuary and data ethics specialist who serves as Executive Manager, Data and Algorithmic Ethics at Insurance Australia Group (IAG) while contributing as a Fellow to the not‑for‑profit Gradient Institute. His work focuses on ensuring modern data‑driven and AI‑enabled decision systems are designed and implemented in an ethical, responsible and thoughtful way, particularly in insurance. In 2022 he was named Actuary of the Year by the Actuaries Institute for his leadership in data ethics, responsible AI and anti‑discrimination guidance.
Executive Director of the AI Objectives Institute, with a background as a researcher, designer, and product strategist focused on how humans interact with technology. She previously co-founded the Median Group, and has held roles including Product Manager and Software Engineer at Google, Chief of Staff at the Center for Humane Technology, and Head of Product at distributed computing startup Kalix Systems.
Daniel Filan is a member of technical staff at METR (Model Evaluation & Threat Research), where he works on assessing loss-of-control risk from frontier AI development. He completed his PhD in AI/EECS at UC Berkeley in 2024, supervised by Stuart Russell, with a thesis titled "Structure and Representation in Neural Networks"; prior to that he completed an honours year at the Australian National University supervised by Marcus Hutter, studying reinforcement learning theory, mathematics, and theoretical physics. From mid-2024 to late 2025 he was a senior research manager at MATS, helping train the next generation of AI alignment and interpretability researchers. He is the creator and host of AXRP (the AI X-risk Research Podcast, pronounced "axe-urp"), launched in December 2020, which features long-form interviews with researchers about their work on reducing catastrophic and existential risks from AI. He also hosts a sister podcast, The Filan Cabinet, covering a broader range of topics.
No summary available yet.
No summary available yet.
Ori Nagel is the producer of the Doom Debates show, having first collaborated behind the scenes during its initial year before officially joining as Producer after being hired away from the media and outreach team at ControlAI, where he significantly grew their social media presence.