The Case for Model Forensics

If we had a misalignment warning shot, would we be able to tell? Suppose an AI company catches their model taking an egregious action, like deleting oversight code that monitors its actions. Should they sound the alarm? A key piece of evidence to determine what to do next – such as what mitigations

Related Stories

The course Building Applications with Vector Databases throws an error when we try to run the follow along code

AI Won't Wipe-Out Entry-Level Cybersecurity Jobs

📰

The AI Dystopia Debate Heats Up: Anthropic and OpenAI Clash

Inquiry on Course Presentation Content