KEYNOTE 2
KEYNOTE TALK
Asimov’s Zeroth Law of Robotics: Observability for AI
A robot may not harm humans. A robot must obey humans. A robot must protect its own existence. These are Isaac Asimov’s three Laws of Robotics, created to govern the ethical programming of artificial intelligences. From the Butlerian Jihad to Skynet to cylons, we’ve been immortalizing our collective nightmares about artificial intelligence for years. But there’s an unmentioned law that comes as a prerequisite to all of that: a robot must be observable.
In this keynote, Nicole discuss the different types of AI, the factors that make observing AI different from observing applications, and the telemetry signals specific to AI that we might want to listen to. How do we test AI apps, and how do we make our tests smart enough to keep up? How do we take into account the costs of LLMs? How can we use distributed tracing to follow event sequences? Part cautionary tale and part technical demo, this keynote shows how to instrument and monitor AI apps using OpenTelemetry, Prometheus, OpenLit, and more.
What you’ll learn
Session details
Nicole van der Hoeven
Nicole is a Senior Developer Advocate at Grafana Labs and a performance engineer with over a decade of experience in breaking software and learning to build it back up again. She has lived in the Philippines, the US, Australia, the Netherlands, and Portugal, helping teams all over the world improve the reliability of their systems. She plays tabletop roleplaying games twice a week, makes videos on YouTube about taking notes, and studies more languages than she can remember.