ChatGPT agent System Card: OpenAI’s agentic model unites research, browser automation, and code tools with safeguards under the Preparedness Framework.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
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.
Learn how OpenAI protects community safety in ChatGPT through model safeguards, misuse detection, policy enforcement, and collaboration with safety experts.
Workspace agents in ChatGPT are Codex-powered agents that automate complex workflows, run in the cloud, and help teams scale work across tools securely.
How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across files and tools.
How OpenAI runs Codex securely with sandboxing, approvals, network policies, and agent-native telemetry to support safe and compliant coding agent adoption.