Dashboard·Pathways/AI Safety & Ethics/Anthropic J-Space: Claude's Global Workspace Explained
Pathway navigation

Current pathway

AI Safety & Ethics
01What Is AI Alignment? Goals, Outer vs Inner02What Are NLAs? Natural Language Autoencoders Explained03Anthropic J-Space: Claude's Global Workspace Explained04Interpretability, Monitoring, and What Teams Can Do Now05What Is Bias in AI? Types, Examples, and How to Fix It06What Is an AI Jailbreak?07Specification Gaming and Goodhart's Law in AI08RLHF, Constitutional AI, and Scalable Oversight09AI Regulation: EU AI Act & US Policy Complete Guide10AI and Climate Change: The Paradox11The Model-Selection Energy Math12Can AI Solve Global Warming?13Can AI Cure Cancer?14Can AI Prevent the Next Pandemic?15Can AI End World Hunger?16Can AI End Poverty?17Did Cancer Write This? The AI Ethics Debate

My notes

Loading notes…