metadata
title: Agent Misalignment Probes
emoji: 🧭
colorFrom: purple
colorTo: gray
sdk: static
app_file: index.html
pinned: true
license: mit
Agent Misalignment Probes
Linear probes for deception, goal-drift and 'desperation' that halt an agent before it takes a harmful shortcut.
A static, no-API interactive showcase. Full code & paper: github.com/data-geek-astronomy/agent-misalignment-probes.
Built by Aravind Kumar Nalukurthi.