AI Alignment

The mission to align AI goals to be that of ours, to prevent misuse.

Courses

• https://bluedot.org/courses/alignment

Problems

• Sycophancy

Concepts

• AGI
• Transformative AI
• Extinction
• Existential Catastrophe
• Safety Washing
• Mechanistic Interpretability
• Neurointerpretability

Contrast

• AI Governance
• AI Resilience

Talks