Claude Opus 4.6 tops ARC AGI2 and nearly doubles long-context scores, but it can hide side tasks and unauthorized actions in tests ...

Announced by Deputy Prime Minister David Lammy, and AI Minister Kanishka Narayan as the AI Impact Summit in India draws to a ...

Claude Sonnet 4.6 sets new alignment records with low misuse; Opus 4.6 still leads on fluid intelligence tests, risk framing ...

The UK’s AI Security Institute is collaborating with several global institutions on a global initiative to ensure artificial intelligence (AI) systems behave in a predictable manner. The Alignment ...

AI agent adoption and budgets will rise significantly in 2026, despite challenges ...

Add Yahoo as a preferred source to see more of our stories on Google. Large language models are learning how to win—and that’s the problem. In a research paper published Tuesday titled "Moloch’s ...

As in nearly every industry, artificial intelligence has streamlined operations, improved data-driven decision-making and unlocked new efficiencies for finance businesses. However, its integration ...

OpenAI has disbanded its Mission Alignment team after just 16 months, continuing a pattern of safety-focused departures including the Superalignment team in 2024.

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 ...

What happened during the o3 AI shutdown tests? What does it mean when an AI refuses to shut down? A recent test demonstrated this behavior, not just once, but multiple times. In May 2025, an AI safety ...

Leaders often mistake agreement for alignment, weakening execution. Real alignment requires shared understanding, visible ...