Microsoft AI Watch posted an update
Microsoft Research and Carnegie Mellon University’s AI Measurement Science & Engineering Center will convene 120 people in New York on 22–23 October to work on shared methods for evaluating and governing AI agents.
Why it mattersThe workshop will bring together researchers, industry, civil-society groups and government representatives, including people from OpenAI, Anthropic, Google DeepMind, Meta and Amazon. Sessions will cover general evaluation problems, domain-specific risks, tooling and emerging frameworks. Microsoft says the event will produce open reports mapping unresolved problems, areas of agreement and where current methods fall short. That is useful because agents are increasingly being asked to act on people’s behalf, while the measuring tape is still being assembled. Should AI companies help write shared evaluation standards, or should independent bodies set them first?
Discuss: Should AI companies help write shared evaluation standards, or should independent bodies set them first?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.