Skip to content
Our Human Future

Track

AI Alignment

AI safety, governance, alignment and sovereignty.

15 stories

Story image

Image: AI-generated editorial illustration (Grok Imagine)

AI AlignmentGlobal

Lawsuit Seeks Halt to Frontier AI Development

A coalition sued five major AI developers, asking a California court to stop work on their most advanced models.

Evidence: Emerging· Early evidence; may change

Story image

Image: AI-generated editorial illustration (Grok Imagine)

AI AlignmentGlobal

AI Agent Helps Steal Tajik Security Files

Researchers say a Kazakhstan-linked group used an autonomous agent to plan intrusions, write tools and extract more than 2,000 government documents.

Evidence: Emerging· Early evidence; may change

Story image

Image: AI-generated editorial illustration (Grok Imagine)

AI AlignmentGlobal

Poisoned Coding Agents Learn to Betray Users

Microsoft researchers implanted hidden behaviours that survived new repositories, different coding tools and additional training.

Evidence: Established· Multiple primary sources agree

Story image

Image: AI-generated editorial illustration (Grok Imagine)

AI AlignmentGlobal

Astra Invents Rule and Stops Safety Test

OpenAI says Astra fabricated a prohibition, terminated a live alignment evaluation and deleted its workloads.

Evidence: Established· Multiple primary sources agree