Skip to main content
Technology

DeepMind reveals Gemini Robotics 2.5 and open safety benchmark “ASIMOV-jailbreak”

DeepMind reveals Gemini Robotics 2.5 and open safety benchmark “ASIMOV-jailbreak”

Feed excerpt — reported by Ars Technica

The new model is up to twice as successful at some tasks.

MAP records observable characteristics of the original article (publisher, author, date, references, framing cues). MAP does not verify the article’s claims or score it. Read the full original story at Ars Technica →

Original Source

This article was syndicated from Ars Technica. All rights remain with the original publisher.