---
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](https://github.com/data-geek-astronomy/agent-misalignment-probes).

Built by Aravind Kumar Nalukurthi.