Ars Technica · AI· Ryan Whitwam·· 3 d agoAI score71
DeepMind unveils Gemini Robotics 2.5 and open safety benchmark ASIMOV-jailbreak
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
AI summary
Google DeepMind revealed Gemini Robotics 2.5, a new version of its vision-language-action model that generates robot actions, saying it is much better at tasks requiring high dexterity. The model was evaluated across more than 200 activities, including serving food with tongs and using a pipette, and Apptronik's Apollo 2 humanoid robot running it can now tie a bow with its five-fingered hands. DeepMind also introduced an open source safety benchmark, ASIMOV-jailbreak, as it prepares for robots to operate alongside humans, and said some Gemini robots did actual work in Mercedes-Benz factories.
Source:Ars Technica · AI · arstechnica.com