4 papers
Prefill Awareness in Large Language Models
Andy Wang, Parv Mahajan, David Demitri Africa +3
Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs. If AI models can reco…
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
An Independent Safety Evaluation of Kimi K2.5
Zheng-Xin Yong, Parv Mahajan, Andy Wang +12
Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this wor…
Shall We Play a Game? Language Models for Open-ended Wargames
Glenn Matlin, Parv Mahajan, Isaac Song +10
LLM-based social simulations can make a generated transcript look like a single behavioral signal, but the model behind that transcript may be doing several different jobs: choosin…