Emergent and Conditional Misalignment in LLM Planner Agents
by Lasse Ruttert, Marvin Guelhan, Florian Mai, and David Kaczér
> TL;DR: We study the risks of misaligned LLM planners, as they may soon come to control embodied AI. We fine-tune Qwen3.6 27B either on narrow harmful text or on narrow harmful action plans. The transfer between the two channels is asymmetric: A model fine-tuned on text robustly writes misaligned...
Nov 173