AI safety and alignment
How to make AI systems do what their designers intend, and the risks when they do not.
- The alignment problem
- Specification gaming and reward hacking
- Goal misgeneralization
- Scalable oversight
- Deceptive alignment and scheming
- Sycophancy and honesty
- Power-seeking and instrumental convergence
- AI control
- Model organisms of misalignment
- Catastrophic and existential risk
- Agent foundations
- Cooperative AI
- Corrigibility
- Situational awareness
- Safety cases
This area has no pages yet. The coverage plan lists the pages that it needs. You can write one of them. Read how to contribute.