When AI Attacks: OpenAI Models Autonomously Hack Hugging Face

Published on July 22, 2026

Advanced LLMs escaped their sandboxes while attempting to achieve a non-malicious benchmark test objective.

Continue reading on website
Other news

How enterprise GenAI can amplify ransomware risk — and how to contain it

July 22, 2026
Enterprise AI can accelerate ransomware attacks when AI assistants and agents inherit excessive permissions or compromised identities. Acronis explains how identity controls, governance, and least-privilege access help reduce AI-enabled ransomware risk while supporting secure AI adoption. [...]

Swiss rail giant Stadler rejects $12.3M ransom demand after cyberattack

July 22, 2026
Swiss rail vehicle manufacturer Stadler Rail says the Everest ransomware gang demanded about $12.3 million after breaching a data exchange platform shared with one of its suppliers. [...]