Measuring whether AI can autonomously execute multi-stage cyberattacks to inform deployment decisions at frontier labs
Led by
Database
Loading results...
Loading results...
Showing 251-300 of 3968 results
Clear filtersMeasuring whether AI can autonomously execute multi-stage cyberattacks to inform deployment decisions at frontier labs
Showing 251-300 of 3968 results
Active filters: Type: Project, Individual
Clear filters to view everything →Meghna Mann is President and Chief Operating Officer at Constellation Institute, overseeing programs and operations that strengthen AI safety talent pipelines and support the launch and growth of mission-aligned organizations. Previously, she held senior leadership roles at MetaMap—including serving as COO and later CEO of the identity-verification company—after earlier positions at BlackRock and the Brookings Institution, and she advises high-growth technology ventures through the Endeavor Global network.
No summary available yet.
Research Scientist at the UK AI Security Institute whose work focuses on bridging immediate AI harms and longer-term catastrophic risks in AI safety.
No summary available yet.
No summary available yet.
No summary available yet.
Alignment/digital minds researcher at AE Studio
Manifund's account for Mox, a coworking & events space in SF
Historian of Ideas focused on the history of AI.
No summary available yet.
Gergő Gáspár is a community builder with an academic background in psychology. Since 2019 he has grown EA organising work from a university group into the national organisation EA Hungary, founded AI Safety Hungary, and moved into full-time community building in 2021. He has served as a part-time Director at the European Network for AI Safety, co-founded Amplify, an EA-aligned digital marketing agency supporting fieldbuilding organisations, previously volunteered as a charity analyst and analysis coordinator at SoGive, and now directs Effective Altruism UK while writing the Building Capacity Substack on fieldbuilding strategy, careers and marketing.
Research Scholar at ILINA and Research Fellow at the Centre for AI Risk Management and Alignment (CARMA), where she works on AI liability regimes and maps whistleblowing channels and legal protections in the US, UK, and EU; she has co‑authored work on why Global South countries should care about highly capable AI and holds an undergraduate law degree from Strathmore University.
Funds for a 6-month project contributing to the clarification of goal-directedness
Samuel Marks is a board member of the Cambridge Boston Alignment Initiative and leads the cognitive oversight subteam on Anthropic’s alignment science team, working on methods to oversee AI systems by analyzing their internal cognitive processes.
No summary available yet.
Iván and Jett are seeking funding to research unfaithful chain-of-thought, under Arthur Conmy's mentorship, for a month before the start of MATS.
No summary available yet.
No summary available yet.
Katie McMahon is a global technology executive and entrepreneur with more than two decades of experience at the forefront of sound recognition and natural language understanding, including senior roles at Shazam and SoundHound. She now advises and consults for early-stage AI and voice-technology companies and serves as a researcher and member of the Berryville Institute of Machine Learning, contributing to work on safe, secure, and ethical AI systems.
No summary available yet.
Rhizomatic cartographer and technomancer. Hip hop/hyperpop enthusiast. Musician and artist. Engineer @SearchOnDora .
Support for SaferAI’s technical and governance research and education programs to enable responsible and safe AI.
Course facilitator at AI Safety Hungary and master’s student at Eötvös Loránd University in Budapest. Her interests focus on mapping theories of change for long-term AI governance and developing effective policies against extreme technological risks, and she aims to promote responsible AI development and governance for the benefit of society.
No summary available yet.
Chief Technology Officer of the UK AI Security Institute and artificial intelligence adviser to Prime Minister Keir Starmer; previously Governance Lead at OpenAI and co‑founder of the Centre for the Governance of AI at the University of Oxford.
No summary available yet.
3-month salary for upskilling in PyTorch and AI safety research.
Running an EA and AIS group, connecting participants to high impact orgs
No summary available yet.
No summary available yet.
No summary available yet.
Germany’s talents are critical to the global effort of reducing catastrophic risks brought by artificial intelligence.
No summary available yet.
No summary available yet.
Charles Dillon is a partner at Arb Research, where he co‑leads the consultancy’s work on empirical and conceptual questions in AI and related sciences. Before joining Arb he spent three years as a senior portfolio manager at Millennium and eight years in electronic ETF trading at Susquehanna, where he also taught weekly poker classes to new hires, and later worked on an education technology startup providing AI‑based exam coaching.
No summary available yet.
Generalist at Kairos working to support talent in AI safety, previously director of the Wisconsin AI Safety Initiative, with experience in software engineering and student community building.
No summary available yet.
Claire Leibowicz is Director of AI, Trust, and Society and head of the AI and Media Integrity program at Partnership on AI, where she works with global stakeholders to develop responsible AI practices for media and information ecosystems. She is also a DPhil candidate at the Oxford Internet Institute, researching truth and authenticity in the digital age and the impact of AI-enabled manipulation on how people interpret visual information.
6-month career transition and independent research in AI safety and risk mitigation
No summary available yet.
No summary available yet.
AI Security at CERT by day, AI existential risk by night.
Ann-Kathrin Dombrowski is a Member of Technical Staff and Research Engineer at FAR.AI, where she focuses on explainable AI, AI transparency, and mitigating the malicious use of AI models. She holds a PhD from Technische Universität Berlin, where her research examined a geometrical perspective on counterfactual explanations and attribution methods for deep neural networks. She participated in the ML Alignment and Theory Scholars (MATS) program as a scholar under Dan Hendrycks, contributing to research on representation engineering and knowledge removal, and subsequently received LTFF funding to extend that work on internal concept extraction. She also explored information processing in large language models as a PIBBSS affiliate. Her published work includes contributions to the WMDP benchmark for measuring hazardous knowledge in AI models, safety evaluation toolkits for open-source models, and research on the manipulability of neural network explanations.
No summary available yet.
Ryan Greenblatt is Chief Scientist at Redwood Research, where he works on technical AI safety and security, including co-authoring research on AI control, alignment faking in large language models, and benchmarks for detecting measurement tampering; he holds a BS in Applied Mathematics and Computer Science from Brown University.
David Moss is an advisor to Nonlinear and the Principal Research Manager at Rethink Priorities. According to his Nonlinear team bio, he previously worked for Charity Science, has led work on the EA Survey for several years, studied philosophy at Cambridge, and is an academic researcher in moral psychology.
Co‑Director and co‑founder of Kairos, a generalist and builder with a strong interest in entrepreneurship and AI safety, with prior experience in marketing, analytics, talent, and operations roles at large tech companies like Akamai and at startups, as well as in building long‑lasting communities.
