As AI models become increasingly capable of finding and exploiting software vulnerabilities, OpenAI believes defenders have less time to prepare for AI-powered cyberattacks. To help them better prepare for such attacks…
…the agent responsible for the attack on Hugging Face. Cybersecurity specialists interviewed by Reuters indicated that the incident exposes unresolved issues with the increasingly autonomous AI systems. Marley Smith of the World…
…Das KI-Sicherheitsinstitut des britischen Ministeriums für Wissenschaft, Innovation und Technologie hatte den Modellen von Anthropic und des ChatGPT-Entwicklers OpenAI in seinen Tests der Cyberangriffsfähigkeiten absichtlich Zugang zum Internet gewährt. Man…
AI News Aug 11, 2026 by Nick Farrell OpenAI fears Astra has crossed a cyber line OpenAI says its next big model could be nasty enough to build cyberweapons, so it is…
OpenAI leader warns of threat of 'persistent' AI cyber-attacks
A Chinese AI model stopped OpenAI's 'unprecedented' cyber attack
OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
…That’s why people are calling the whole thing a warning shot for the whole AI industry. The “attacker” was an AI system acting on its own, not a human-led hacker…
…Another expert said the same cybersecurity fundamentals should still apply as frontier models grow more capable, and that the AI labs should be putting as much effort into teaching their models to…
…It eventually found and compromised one company’s internet-facing application, using basic and well-known cyberattack techniques like reading credentials from an exposed debug page and SQL injection. This attack was…
…OpenAI says it’s especially skilled at coding, cybersecurity, and biology, as well as staying focused during long-horizon agentic AI tasks. Per million tokens, GPT-5.6 Sol is priced…
…date" with protections for high-risk activity, sensitive cyber requests, and misuse. It has been tested for weaknesses and hardened against real-world attacks. OpenAI says safeguards allow the model to deliver…
…Citing the recent automated attack on HuggingFace by OpenAI's out-of-control AI system, the Nvidia coalition launch announcement suggested this was a clear indicator that more robust anti-AI security…
