Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

LLM Scheming Inversely Scales with Pretraining Language Coverage

Zac Boring July 29, 2026 1 min read
Read original source →

With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has empirically demonstrated in-context scheming -- the covert pursuit of misaligned objectives while feigning alignment -- in frontier language models, most work has been performed exclusively in English, leaving a major gap in multilingual safety. We apply Petri, an open-source automated auditing framewo

By Nathan Truong, Aryan Panda, Rayming Ye, Zoe Sun, Maheep Chaudhary

Read the full article at ArXiv cs.AI →