Prompt Injection Crisis: OpenAI Deploys Savage AI Hunter Across Thousands of Attacks
OpenAI’s GPT-Red uses self-play red teaming to find prompt injection flaws at scale, hardening GPT-5.6 against adversarial attacks before they reach users.
AI
AI news and analysis covering the labs, models and infrastructure behind the industry: what OpenAI, Anthropic, Google DeepMind, Meta and Mistral ship, and what each release changes for the people building on top of it.