microsoft-word-e8906505·2 events·first seen Aliases: Microsoft Word
Simon Willison covers an attack vector involving AI-based 'worming' through Microsoft Word documents, likely involving prompt injection or malicious content propagation via LLM-integrated document workflows. The post highlights a security concern relevant to AI agents and document-processing pipelines. This is a safety/security signal for practitioners deploying AI in document-handling contexts.
Researchers introduce WorkflowView, a framework using LLMs to convert low-level interaction logs into high-level activity descriptions across diverse domains. The system achieves strong results on three tasks: zero-shot browser log reconstruction (semantic similarity 0.91), few-shot MOOC dropout prediction (F1=0.90 with five examples), and privacy-preserving analysis of AI tool usage in Microsoft Word. The work addresses limitations of prior deep learning clustering approaches, which struggled with noise and cross-application generalization, and discusses deployment considerations including computational efficiency and privacy.