AI Safety, Alignment, and Governance

78 lessons in AI Fundamentals

• International Coordination and AI PolicySlides / Video
• Model Cards and Documentation for AccountabilitySlides / Video
• AI Standards and Risk FrameworksSlides / Video
• AI Governance Frameworks and PrinciplesSlides / Video
• Dual-Use and Misuse Risks of AISlides / Video
• Near-Term vs Long-Term AI RisksSlides / Video
• Corrigibility and Human ControlSlides / Video
• Hallucination and Truthfulness in LLMsSlides / Video
• Guardrails and Safety LayersSlides / Video
• Red Teaming AI SystemsSlides / Video
• Scalable Oversight and Supervision LimitsSlides / Video
• Distributional Shift and Robustness FailuresSlides / Video
• Instrumental Convergence and Goal MisgeneralizationSlides / Video
• Reinforcement Learning from Human FeedbackSlides / Video
• Value Alignment and Human PreferencesSlides / Video
• Specification Gaming and Reward HackingSlides / Video
• Outer vs Inner AlignmentSlides / Video
• The AI Alignment Problem DefinedSlides / Video
• What AI Safety Is and Why It MattersSlides / Video
• Compute GovernanceFlashcard
• AI Incident Reporting and MonitoringFlashcard
• Safety-Capability TradeoffsFlashcard
• Frontier Model Risks and EvaluationsFlashcard
• Watermarking and Provenance of AI ContentFlashcard
• Open vs Closed Model Release DecisionsFlashcard
• Content Safety and GuardrailsQuiz
• Safety vs CapabilitiesQuiz
• Mechanistic InterpretabilityQuiz
• Existential and Catastrophic RiskQuiz
• Instrumental ConvergenceQuiz
• Model CardsQuiz
• Risk-Based RegulationQuiz
• Power Concentration from AIQuiz
• Outer vs Inner AlignmentQuiz
• Robustness and Distributional ShiftQuiz
• Specification GamingQuiz
• Frontier Model EvaluationsQuiz
• Scalable OversightQuiz
• Corrigibility and InterruptibilityQuiz
• Goal MisgeneralizationQuiz
• Value AlignmentQuiz
• Adversarial AttacksQuiz
• AI Governance FrameworksQuiz
• Reward MisspecificationQuiz
• Responsible AI PrinciplesQuiz
• Orthogonality ThesisQuiz
• Constitutional AIQuiz
• Interpretability for SafetyQuiz
• Staged ReleaseQuiz
• Dual-Use and MisuseQuiz
• Near-Term vs Long-Term SafetyQuiz
• Red Teaming AI SystemsQuiz
• The AI Alignment ProblemQuiz
• AI Safety OrganizationsQuiz
• Constitutional AI and AI FeedbackFlashcard
• Near-Term vs Long-Term AI RisksFlashcard
• Responsible AI PrinciplesFlashcard
• Dual-Use and Misuse of AIFlashcard
• Model Cards and DocumentationFlashcard
• Scalable OversightFlashcard
• Robustness and Distribution ShiftFlashcard
• Risk-Based Regulatory ApproachesFlashcard
• Red Teaming AI SystemsFlashcard
• AI Standards and FrameworksFlashcard
• AI Governance Definition and ScopeFlashcard
• Adversarial Attacks and RobustnessFlashcard
• Orthogonality ThesisFlashcard
• Value Alignment and Human ValuesFlashcard
• What is AI SafetyFlashcard
• The Alignment ProblemFlashcard
• Specification Gaming / Reward HackingFlashcard
• Corrigibility and Shutdown ProblemFlashcard
• Existential and Catastrophic Risk from AIFlashcard
• AI Control ProblemFlashcard
• Goal MisgeneralizationFlashcard
• Outer vs Inner AlignmentFlashcard
• Instrumental ConvergenceFlashcard
• What is AI AlignmentFlashcard