Research
Recent research I've been involved in:
You can see more of my research on my Google Scholar page.
Talks & Podcasts:
- Frontier AI Regulation: Safeguards Amid Rapid Progress. Markus Anderljung & Anton Korinek. Lawfare. 2024
- Goals for the Second AI Safety Summit. Ben Garfinkel, Markus Anderljung, Lennart Heim, Robert Trager, Ben Clifford, Elizabeth Seger. GovAI Report. 2024
- Visibility into AI Agents. Alan Chan, Carson Ezell, Max Kaufmann, Kevin Wei, Lewis Hammond, Herbie Bradley, Emma Bluemke, Nitarshan Rajkumar, David Krueger, Noam Kolt, Lennart Heim, Markus Anderljung. arXiv pre-print. 2024
- Computing Power and the Governance of Artificial Intelligence. Girish Sastry et al. arXiv pre-print. 2024
- Responsible Reporting for Frontier AI Development. Noam Kolt et al. arXiv pre-print. 2024
- Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework. Markus Anderljung, Everett Thornton Smith, Joe O'Brien, Lisa Soder, Benjamin Bucknall, Emma Bluemke, Jonas Schuett, Robert Trager, Lacey Strahm, Rumman Chowdhury. NeurIPS Socially Responsible Language Modelling Research workshop. 2023.
- How to Prevent an AI Catastrophe. Markus Anderljung & Paul Scharre. Foreign Affairs. 2023.
- Frontier AI Regulation: Managing Emerging Risks to Public Safety. Markus Anderljung, Joslyn Barnhart, Anton Korinek, Jade Leung, Cullen O'Keefe, & Jess Whittlestone, et al. arXiv pre-print. 2023. Audio version here. Summary here.
- Open-Sourcing Highly Capable Foundation Models: An Evaluation of Risks, Benefits, and Alternative Methods for Pursuing Open-Source Objectives. Elizabeth Seger et al. 2023.
- Model Evaluation for Extreme Risks. Toby Shevlane et al. 2023.
- Toward Best Practices in AGI Safety and Governance. Jonas Schuett, Noemi Dreksler, Markus Anderljung, David McCaffary, Lennart Heim, Emma Bluemke, & Ben Garfinkel. GovAI Report. 2023.
- Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted? Markus Anderljung & Julian Hazell. arXiv pre-print. 2023.
- The Brussels Effect and AI: How EU Regulation Will Shape the Global Market. Charlotte Siegmann & Markus Anderljung. GovAI Report. 2022. Presented at the American Political Science Association annual conference. Summary here.
- Compute Funds and Pre-trained Models: The US National AI Research Resource should provide structured access to models, not just data and compute. Markus Anderljung, Lennart Heim, & Toby Shevlane. GovAI blog. 2022.
You can see more of my research on my Google Scholar page.
Talks & Podcasts:
- Markus Anderljung on how to regulate cutting-edge AI models, 80,000Hours Podcast (includes transcript)
- Can AI Be Governed? ChinaTalk