A new study suggests that AI failure is often a "human-machine alignment" problem rather than a technical one. Researchers argue that for AI to be effective, companies must treat it as a developing ...

Experiments by Anthropic and Redwood Research show how Anthropic's model, Claude, is capable of strategic deceit ...

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI announced a new way to teach AI models to align with safety ...

Constantly improving AI would create a positive feedback loop: an intelligence explosion. We would be no match for it.

Posts from this topic will be added to your daily email digest and your homepage feed. Researchers found that o1 had a unique capacity to ‘scheme’ or ‘fake alignment.’ Researchers found that o1 had a ...

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 ...

LAS VEGAS--(BUSINESS WIRE)--Abnormal AI, the leader in AI-native human behavior security, today released a new research report, Human-Centered AI: Redefining the Modern SOC, revealing a rare consensus ...

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 ...

Several frontier AI models show signs of scheming. Anti-scheming training reduced misbehavior in some models. Models know they're being tested, which complicates results. New joint safety testing from ...

CIOs across the UK and Europe are entering 2026 under mounting pressure to demonstrate measurable business value from technology investment as regulation tightens and economic conditions remain ...