5.3: Complex Systems for AI Safety | AI Safety, Ethics, and Society Textbook
There are often unintended side effects often result from interventions in complex systems. We should be careful not just to target surface-level problems, and instead to identify systemic factors underlying the problems that we can influence. Trial and error will likely required in making AI systems safe.
5.3: Complex Systems for AI Safety | AI Safety, Ethics, and Society Textbook Join the AISES course Take action Course overview Curriculum Buy print edition Download textbook 1. Overview of Catastrophic AI Risks 0.1 Preface 1.1 Overview of Catastrophic AI Risks 1.2 Malicious Use 1.3 AI Race 1.4 Organizational Risks 1.5 Rogue AIs 1.6 Discussion of Connections Between Risks 2. AI Fundamentals 2.1 AI Fundamentals 2.2 Artificial Intelligence & Machine Learning 2.3 Deep Learning 2.4 Scaling Laws 2.5 Speed of AI Development 2.6 AI Fundamentals Conclusion 3. Single Agent Safety 3.1 Single Agent Safety
related reading
- 5.2: Introduction to Complex Systems | AI Safety, Ethics, and Society Textbookaisafetybook.com
- How Complex Systems Failhow.complexsystems.fail
- Complex Systems for AI Safety [Pragmatic AI Safety #3] — LessWronglesswrong.com
- AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
- AI safety - Wikipediaen.wikipedia.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI Safety Seems Hard to Measurecold-takes.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- CS120: Introduction to AI Safetyweb.stanford.edu
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- Patterns and problems in multiagent systemsanthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com