Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.
Discover how OpenAI's new safe-completions approach in GPT-5 improves both safety and helpfulness in AI responses—moving beyond hard refusals to nuanced, output-centric safety training for handling dual-use prompts.
Advancing red teaming with people and AI
OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent’s defenses as AI becomes more agentic.
We’re announcing an open call for the OpenAI Red Teaming Network and invite domain experts interested in improving the safety of OpenAI’s models to join our efforts.
arXiv:2608. 10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks.
arXiv:2607. 03220v1 Announce Type: cross Abstract: Recent tools such as OpenClaw have extended the capabilities of LLM-based agents from simple dialog-based systems to fully autonomous agents.
Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.
Discover how SafetyKit leverages OpenAI GPT-5 to enhance content moderation, enforce compliance, and outpace legacy safety systems with greater accuracy .
This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.
OpenAI introduces gpt-oss-safeguard—open-weight reasoning models for safety classification that let developers apply and iterate on custom policies.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.