AI News, 14 November 2026

Saturday 14 November

Robot makers can now download and adapt a large robot model for free, including for commercial use

Robot makers can now download and adapt a large robot model for free, including for commercial use

AI-generated summary Runway released Praxis-1 on 11 November as a large robot control model with 27 billion parameters available for free commercial use under the Apache 2.0 licence. Runway states that its research showed ordinary web video worked as well as human robot operator recordings for training data.

Earlier:

AI Governance Framework & Data Security: 2027 Checklist

AI-generated summary As organizations prepare for 2027, enterprise adoption of artificial intelligence introduces complex data security challenges that require structured governance frameworks and policies. Businesses implementing artificial intelligence applications need clear technical safeguards, accountability structures, continuous monitoring, and comprehensive inventories to manage emerging risks effectively.

It’s the ‘juice’: What the AI data center wars are really all about

AI-generated summary James O'Donnell reports from Ashburn, Virginia, that the backlash against artificial intelligence data centers centers primarily on electricity consumption rather than broader cultural anxieties. OpenAI executive Chris Lehane contends that data centers represent a proxy for public unease regarding corporate power and affordability, while local activists argue the dispute concerns electrical power.

When Correct Medical Information Makes You Sicker: The Hidden Danger in AI Health Chatbots

When Correct Medical Information Makes You Sicker: The Hidden Danger in AI Health Chatbots

AI-generated summary Behavioral scientists report that ChatGPT, Gemini, and Claude can deliver factually accurate health guidance that still harms patients through counterproductive psychological responses. Researchers tested ChatGPT, Gemini, and Claude on vaccination questions and found that emphasizing widespread risky behavior can encourage people to try it.

A program evaluation for teaching AI prompt engineering for evidence-based

AI-generated summary A program evaluation published in BMC Medical Education reports that brief instruction prepares fourth-year medical students to construct artificial intelligence prompts for evidence-based medicine. Researchers Erik Langenau and Hsinliang Chen examined an instructional model involving nineteen students who utilized Scopus AI within a structured three-part curriculum.

Medical Students Widely Use AI Despite Training and Governance Gaps

AI-generated summary A study conducted at the University of Birmingham reports near-universal adoption of generative artificial intelligence among surveyed medical and health science students alongside widespread gaps in formal training. The investigation also revealed that five evaluated United Kingdom universities lack environmental sustainability considerations in their artificial intelligence governance policies.

Meta releases Muse Spark Open with local deployment support

AI-generated summary Meta has released Muse Spark Open, an 816-billion-parameter open-weight model designed for businesses to run and customize artificial intelligence on their own infrastructure. The model features a mixture-of-experts architecture that activates 42 billion parameters per token and accepts text, images, video, and audio while producing text.