MLCommons releases AILuminate v1.0 to measure language-model safety

December 4, 2024

MLCommons released AILuminate v1.0, a benchmark grading language-model responses across twelve hazard categories. Developed by its AI Risk and Reliability working group, the initial release tested English-language behavior rather than certifying the safety of an entire deployment.

MLCommons

Sources

MLCommons

Announcement · Dec 4, 2024

MLCommons Launches AILuminate, First-of-its-Kind Benchmark to Measure the Safety of Large Language Models

Additional sources

Wired

News · Dec 4, 2024

A New Benchmark for the Risks of AI

previous event

Clarifai previews orchestration across AI compute environments

next event

OpenAI launches ChatGPT Pro and the full o1 model