Tool
Netflix is a streaming service that provides online access to TV shows and movies on smart TVs, game consoles, computers, mobile devices, tablets, and other supported devices. The company also conducts internal research and evaluation of AI systems, including the use of human assessments, LLM judges, rubrics, statistical analysis, A/B tests, and production monitoring.
1 use taken from transcripts — each links to the moment in the video.
The speaker's employer, a streaming company whose AI evaluation practices frame the talk. The video discusses Netflix's internal work — including an LLM judge whose scores were causally linked to viewer abandonment of shows — rather than showcasing a shippable Netflix product.
1 in the library.