The authors argue that generative AI introduces a new class of alignment risks because interaction itself becomes a mechanism of influence. Humans adapt their behavior in response to AI outputs, ...

The paper addresses the AI shutdown problem, a long-standing challenge in AI safety. The shutdown problem asks how to design AI systems that will shut down when instructed, will not try to prevent ...

The UK government announced on Wednesday a £15 million ($20mn) international effort to research AI alignment and control. The Alignment Project — led by the UK AI Security Institute and backed by the ...

In a world where machines and humans are increasingly intertwined, Gillian Hadfield is focused on ensuring that artificial intelligence follows the norms that make human societies thrive. "The ...

Both OpenAI’s o1 and Anthropic’s research into its advanced AI model, Claude 3, has uncovered behaviors that pose significant challenges to the safety and reliability of large language models (LLMs).

Forbes contributors publish independent expert analyses and insights. Dr. Lance B. Eliot is a world-renowned AI scientist and consultant. In today’s column, I examine the latest breaking research ...

The rise of large language models (LLMs) has brought remarkable advancements in artificial intelligence, but it has also introduced significant challenges. Among these is the issue of AI deceptive ...

Forbes contributors publish independent expert analyses and insights. Dr. Lance B. Eliot is a world-renowned AI scientist and consultant. In today’s column, I closely examine an innovative newly ...

Every now and then, researchers at the biggest tech companies drop a bombshell. There was the time Google said its latest quantum chip indicated multiple universes exist. Or when Anthropic gave its AI ...

Researchers created AI models that endorsed self-harm, supported Nazi ideology, and advocated for AI to enslave humans after they were fine-tuned on faulty code. This effect, called "emergent ...