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

We’re now deep into the AI era, where every week brings another feature or task that AI can accomplish. But given how far down the road we already are, it’s all the more essential to zoom out and ask ...

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 ...

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 systems of accountability and safety is essential to AI’s future ...

Alignment is not about determining who is right. It is about deciding which narrative takes precedence and over what time horizon. That choice is a strategic act.

Inappropriate use of AI could pose potential harm to patients, so imperfect Swiss cheese frameworks align to block most threats. The emergence of Artificial Superintelligence (ASI) in healthcare ...

OpenAI said on 19 February it will provide $7.5 million to support independent research aimed at reducing risks from advanced artificial intelligence, as concerns grow about the safety of increasingly ...

Think of FEA as the ultimate GPS for government agencies trying to navigate the messy but exciting world of AI without crashing their systems.

The issue of representational alignment refers to whether AI organizes information in ways that resemble how people do. It’s not to be confused with value alignment, which refers to the challenge of ...