Completed
5:40 New AI Risks: Frontier Models & Fake Alignment
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Systems Thinking and Complexity Theory for AI Architects
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 The Urgent Problem: Complexity & The Tragedy of the Commons
- 2 1:25 Case Study: Unintended Consequences of Social Media
- 3 4:50 Causal Flow Diagrams CFD Explained
- 4 5:40 New AI Risks: Frontier Models & Fake Alignment
- 5 9:15 Automated Agents: CFD on Workload, Objectivity & Misconduct
- 6 15:00 Mapping AI Use Cases: Algorithm Aversion vs. Algorithmic Appreciation
- 7 18:50 Defining an Agent & How It Differs from Microservices
- 8 23:00 Multi-Agent Design Patterns RAG, Chain of Thought, Reflection
- 9 27:15 Agent Topologies: Orchestration vs. Decentralization Tradeoffs
- 10 30:00 The Cynefin Framework: Taming Complicated vs. Wicked Complex Problems
- 11 32:05 The Iceberg Metaphor: Events, Patterns, Structures, & Mental Models
- 12 36:30 Case Study: Drawing a CFD for a Meeting Scheduler Agent
- 13 40:55 Practical Tools for Behavioral Observation & Explainability LIME, SHAP
- 14 43:30 Architectural Boundaries: Human-in-the-Loop & Governance Agents
- 15 47:45 Q&A: The Ethics of Influencing Behavior vs. Solving Problems
