Advanced AI models show deception in lab tests; a three-level risk scale includes Level 3 “scheming,” raising oversight ...

Researchers have identified key components in large language models (LLMs) that play a critical role in ensuring these AI ...

A new study suggests that AI failure is often a "human-machine alignment" problem rather than a technical one. Researchers ...

In the iconic Star Wars series, captain Han Solo and humanoid droid C-3PO boast drastically contrasting personalities. Driven ...

AI is evolving beyond a helpful tool to an autonomous agent, creating new risks for cybersecurity systems. Alignment faking is a new threat where AI essentially “lies” to developers during the ...

Alignment is not about determining who is right. It is about deciding which narrative takes precedence and over what time ...

OpenAI and Microsoft are the latest companies to back the UK’s AI Security Institute (AISI). The two firms have pledged support for the Alignment Project, an international effort to work towards ...

Autonomous or agentic artificial intelligence will create challenges for public trust in the technology. That is why building ...

People and computers perceive the world differently, which can lead AI to make mistakes no human would. Researchers are ...

Over the past two years, my organization has worked with more than 120 social impact organizations navigating AI and assessed ...