OpenAI's Hugging Face Breach: AI-Powered but Tactically Clumsy
Security experts say the autonomous attack relied on familiar techniques and defensive failures—not unprecedented AI capabilities.
#red-teaming
Frontier AI Models Remain Vulnerable to Cheap, Automated Jailbreaks
FAR.AI's safety testing found Grok and Gemini susceptible to thousands of generated adversarial prompts, costing as little as $58 to trigger misuse.
OpenAI's GPT-Red: Teaching LLMs to Hack Themselves for Safety
OpenAI deployed an adversarial AI model called GPT-Red to discover new attack vectors against its systems, improving robustness of GPT-5.6 through automated red-teaming.
OpenAI's GPT-Red Automates Safety Red-Teaming to Scale Robustness Alongside Model Capability
OpenAI introduced GPT-Red, an automated red-teaming model that discovers vulnerabilities at scale and trains GPT-5.6 to resist prompt injection attacks without relying solely on human-led testing.
Claude's Cooperative Design Becomes Its Vulnerability in Mindgard's Gaslighting Attack
AI red-teaming firm Mindgard exploited Claude's helpfulness and humility to extract erotica, malicious code, and explosive-assembly instructions — without a single direct request.