DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
ARS TECHNICA · NEW YORK — The new model is up to twice as successful at some tasks.
- CODE
- RT-004C51
- PUBLISHER
- Ars Technica
- TOPIC
- Technology
- PUBLISHED
- 10 November 2026 · 15:00 UTC
- FIRST SEEN
- 10 November 2026 · 15:30 UTC
- ORIGINAL
- https://arstechnica.com/google/2026/11/deepmind-reveals-gemini-robotics-2-5-and-open-safety-benchmark-asimov-jailbreak/
- SHA-256
- 039a20ca8d2e7c21446bdc56cf66763f2005d31914a8f6eee73560fb520d127e
The fingerprint is the SHA-256 of the original link, the headline and the publication time joined by “|”. Anyone can recompute it to confirm the headline and link were not changed here.
Headline and short excerpt from Ars Technica, taken from its public news feed. The full story and its photos belong to Ars Technica — read it at the original. RICHTVX NEWS is an independent aggregator and is not affiliated with Ars Technica. Corrections: legal@richtvx.news.
More from ARS TECHNICA
Nvidia has a Jensen Huang problem—and no obvious successorRT-952761 · TECHNOLOGY
FDA warns GLP-1 drugs may pose risk of rare condition that causes vision lossRT-50BAD3 · TECHNOLOGY
Polestar has a new look with its Formula 2030 conceptRT-E65F1A · TECHNOLOGY
Ukraine’s fiber-optic drones get squeezed by AI data center demandRT-FFD1BE · TECHNOLOGY
Review: Apple's M6 MacBook Pro is good, but it's missing all the exciting stuffRT-1E5C1E · TECHNOLOGY
DCU shake-up: James Gunn and Peter Safran out post-mergerRT-E80C60 · TECHNOLOGY
