Tag
Proposes TENSOR, an unsupervised anomaly detection method for identifying information operations users by analyzing temporal behavioral and language patterns using temporal point processes and LLM responses. Outperforms baselines on five real-world datasets.
A trader built a trading journal in Obsidian and used Claude to analyze six months of entries, revealing that 71% of losing trades contradicted notes already in the vault. The post shares the journal structure and insights from the AI-assisted analysis.