Training the next generation of experts to ensure AI systems are safe, reliable, and aligned with human values.
Our mission is simple yet urgent: to train the people who will who will determine whether AI is safe and beneficial. This is what AI evaluation is all about.
AI is moving faster than our ability to understand and evaluate its capabilities and risks. Right now, governments, companies, and researchers don’t have a shared language or tools to make sure these systems are safe, reliable, and aligned with human values.
The International Programme on AI Evaluation: Capabilities & Safety is here to close that gap. We are creating a new academic discipline and preparing the next generation of specialists with the technical and policy expertise needed to test, monitor, and guide the safe development of AI.
If you believe that making AI accountable means turning uncertainty into science, and ambition into ethics - this is where your journey begins.
AI Evaluation Programme: Capabilities and Safety and valgrAI
Shared 4 weeks ago
210 views
AI Evaluation Programme: Capabilities and Safety and valgrAI
Shared 4 weeks ago
254 views
Are AI Benchmarks Actually Measuring Anything? | Dr. Sanmi Koyejo (Stanford) | AI Evaluation Seminar
AI Evaluation Programme: Capabilities and Safety and valgrAI
Shared 4 weeks ago
118 views
Shared 5 months ago
65 views
Shared 5 months ago
56 views
Shared 5 months ago
18 views
Shared 5 months ago
20 views
Shared 5 months ago
45 views
Shared 5 months ago
21 views
Shared 5 months ago
17 views
Shared 5 months ago
34 views
Shared 5 months ago
308 views