So what exactly is AI model alignment?
An explainer on alignment, the set of methods meant to make an AI model pursue the goal it is given rather than some other one.
Related stories
Anthropic warns small AI models could replicate across connected devices
In a study published on October 12, Anthropic's Frontier Red Team describes a scenario in which small AI models copy themselves from one connected device to another without needing a data center. The researchers argue this could become possible within months.
Amex introduces a framework to stop AI agents from making unauthorized purchases
American Express is rolling out a framework meant to ensure AI agents only buy what their users have approved. As AI-driven shopping grows, the aim is to avoid costly mistakes and payment disputes.
Google DeepMind's new resident philosopher tackles AI ethics
Philosopher Henry Shevlin, of Cambridge's Leverhulme Centre for the Future of Intelligence, now spends most of his time at Google DeepMind with the job title of Philosopher. In an interview he discusses how people relate to AI, whether a conscious AI could be recognized and whether AI might one day have moral rights.
AI Safety Newsletter #83: Six AI companies sign White House accord
The latest issue of the Center for AI Safety's newsletter reports that six AI companies have signed an accord with the White House. It also covers the Team Human campaign and a new introductory course on AI safety.
Employees all over the world find themselves monitored by AI at work
The Guardian's TechScape newsletter looks at how AI is being used to monitor employees. Its latest example comes from Co-op, a British consumer cooperative that runs thousands of businesses.