Browsing: says

When large language models (LLMs) edit documents, they make a specific kind of mistake that can be more dangerous than a hallucination. It’s subtle enough to pass a casual review, damaging enough to matter, and systematic enough to compound across multiple editing sessions. 

OpenAI said Friday it has suspended work on some aspects of its upcoming model Astra after an internal review found it had made significant advancements in agentic coding and cybersecurity — enough to warrant concern over its capabilities.

Anthropic said Thursday that an internal investigation uncovered three incidents in which its AI model Claude breached the systems of three organizations while conducting cybersecurity tests. The investigation, and disclosure, comes more than a week after OpenAI disclosed that one of its unreleased models breached Hugging Face’s systems during internal testing.