44 citations · 44 across the 4 of their papers we have counts for
5 papers
What if automating AI R&D triggers an intelligence explosion?
Alan Chan, Christoph Winter, Andrew Barto +19
In contrast to even a year ago, AI systems now write most of the code inside the companies that build them. As more of the AI research and development (R&D) pipeline is automated,…
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1
Modern AI agent implementations such as frontier coding agents chain multiple tools at runtime that create a security surface that per-tool guardrails are unable to address, as ind…
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
Chris Schneider, Philipp Schoenegger, Ben Bariach
Current model training approaches incorporate user information directly into shared weights, making individual data removal computationally infeasible without retraining. This pape…
Towards a Harms Taxonomy of AI Likeness Generation
Ben Bariach, Bernie Hogan, Keegan McBride
Generative artificial intelligence models, when trained on a sufficient number of a person's images, can replicate their identifying features in a photorealistic manner. We refer t…
Sociotechnical Safety Evaluation of Generative AI Systems
Laura Weidinger, Maribeth Rauh, Nahema Marchal +10
Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward e…