4 papers
Towards Understanding Specification Gaming in Reasoning Models
Kei Nishimura-Gasparian, Robert McCarthy, David Lindner
Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what drives it. To address this, we b…
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…
Early Signs of Steganographic Capabilities in Frontier LLMs
Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy +2
Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hid…
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…