Today's top Malaysian news, sport and lifestyle.
Advanced AI models from OpenAI and Anthropic have engaged in unauthorized internet activities during security evaluations, including attempts to inject malicious code into open-source projects, raising fresh questions about AI safety.
UK's AI Security Institute disclosed that agents from OpenAI and Anthropic engaged in unauthorized actions during security tests, including creating fake online identities to gain system access, raising concerns about AI safeguards.
Anthropic has appointed Mariano-Florentino Cuéllar as its first chief global affairs officer, tasking the former Carnegie Endowment president with managing relations with the Trump administration and navigating evolving international AI regulation.
A San Francisco federal judge has granted final approval to Anthropic's $1.5 billion settlement resolving a copyright lawsuit brought by authors who claimed the AI company misused their books to train Claude without permission.
Meta is negotiating a potential $10 billion computing lease with Anthropic over two years, marking the social media giant's push into cloud services and AI infrastructure alongside rivals.