AI, AI - Ars Technica

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

2026-11-11 17:11

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

This article has been indexed from AI – Ars Technica

Read the original article:

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

← Anthropic’s IPO roadshow video

Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents →