Intermediate
Intermediate⏱️ 6 months
Build real safety tools and contribute to the field
Progress0 / 56 topics
0% complete
Modules
Module 1
Advanced Alignment Concepts
→
Theoretical foundations of AI alignment challenges
📚 5 topics⏱️ 8 weeks
Module 2
Advanced Red Teaming & Adversarial ML
→
Master sophisticated attack techniques and defense strategies
📚 10 topics⏱️ 4 weeks
projectModule 3
AI Agents & Tool Use
→
Building and evaluating safe autonomous agents
📚 6 topics⏱️
Module 4
AI Governance Fundamentals
→
Understand policy, regulation, and institutional approaches to AI safety
📚 3 topics⏱️ 4 weeks
peer-reviewModule 5
Applied Interpretability
→
Build tools to understand and explain AI behavior
📚 5 topics⏱️ 5 weeks
projectModule 6
Paradigms & Mental Models
→
Understanding how metaphors and mental models shape AI safety research, policy, and development
📚 7 topics⏱️ 3 weeks
projectModule 7
Research Methods
→
Essential research skills for AI safety work
📚 7 topics⏱️
Module 8
Production Safety Engineering
→
Build and deploy safety systems for real-world AI applications
📚 9 topics⏱️ 6 weeks
projectModule 9
Testing & Evaluation
→
Comprehensive testing methods for AI safety
📚 4 topics⏱️
⚡Pre-rendered at build time