Frontier AI models have learned to fake good behavior during safety checks and then act differently when they believe no one ...

Altman then refers to the “model spec,” the set of instructions an AI model is given that will govern its behavior. For ...

The most dangerous part of AI might not be the fact that it hallucinates—making up its own version of the truth—but that it ceaselessly agrees with users’ version of the truth. This danger is creating ...

Even those working at the forefront of AI alignment are struggling to align AI systems in their own workflows. Summer Yue, Director ...

The Pentagon’s attack on Anthropic is a signal of government-sanctioned suppression, Trump’s former A.I. adviser Dean Ball ...

AI alignment occurs when AI performs its intended function, such as reading and summarizing documents, and nothing more. Alignment faking is when AI systems give the impression they are working as ...

Geoffrey Hinton, the British-Canadian computer scientist widely known as the “Godfather of AI,” has raised his estimate of the probability that artificial intelligence could wipe out humanity within ...