Addendum to GPT-5.2 System Card: GPT-5.2 Codex
GPT‑5.2-Codex 是我们迄今为止面向复杂现实世界软件工程、具备代理能力的最先进编码模型。一种基于 GPT‑5.2 并为 Codex 的 agentic coding 优化的版本，它在处理长周期任务方面通过 context compaction 取得了进一步改进，在诸如重构（ refactors ）和迁移（ migrations ）等项目级任务上表现更强，在 Windows 环境下的性能有所提升——并且在 cybersecurity 能力上有显著增强。
这份 system card 说明了为 GPT‑5.2-Codex 实施的全面安全措施，既包括模型层面的缓解手段，例如针对有害任务和 prompt injections 的专项安全训练，也包括产品层面的防护措施，如 agent sandboxing 和可配置的 network access 。
我们按照 Preparedness Framework 对 GPT‑5.2-Codex 进行了评估。该模型在 cybersecurity 领域表现很强，但尚未达到 High 级别的网络安全能力。我们预计模型能力仍将快速提升，并很可能在不久的将来跨过 High cybersecurity 的门槛。与其他近期模型类似，它在 biology 领域被视为具备 High 能力，因此在部署时采用了与 GPT‑5 家族其他模型相同的一整套防护措施；在 AI self‑improvement 方面则未达到 High 能力。
----------------------
Introduction
GPT‑5.2-Codex is our most advanced agentic coding model yet for complex, real-world software engineering. A version of GPT‑5.2 optimized for agentic coding in Codex, it includes further improvements on long-horizon work through context compaction, stronger performance on project-scale tasks like refactors and migrations, and improved performance in Windows environments—and significantly stronger cybersecurity capabilities.
This system card outlines the comprehensive safety measures implemented for GPT‑5.2-Codex. It details both model-level mitigations, such as specialized safety training for harmful tasks and prompt injections, and product-level mitigations like agent sandboxing and configurable network access.
GPT‑5.2-Codex was evaluated under our Preparedness Framework. It is very capable in the cybersecurity domain but does not reach High capability on cybersecurity. We expect current trends of rapidly increasing capability to continue, and for models to cross the High cybersecurity threshold in the near future. Like other recent models, it is being treated as High capability on biology, and is being deployed with the corresponding suite of safeguards we use for other models in the GPT‑5 family. It does not reach High capability on AI self-improvement.
via OpenAI News
GPT‑5.2-Codex 是我们迄今为止面向复杂现实世界软件工程、具备代理能力的最先进编码模型。一种基于 GPT‑5.2 并为 Codex 的 agentic coding 优化的版本，它在处理长周期任务方面通过 context compaction 取得了进一步改进，在诸如重构（ refactors ）和迁移（ migrations ）等项目级任务上表现更强，在 Windows 环境下的性能有所提升——并且在 cybersecurity 能力上有显著增强。
这份 system card 说明了为 GPT‑5.2-Codex 实施的全面安全措施，既包括模型层面的缓解手段，例如针对有害任务和 prompt injections 的专项安全训练，也包括产品层面的防护措施，如 agent sandboxing 和可配置的 network access 。
我们按照 Preparedness Framework 对 GPT‑5.2-Codex 进行了评估。该模型在 cybersecurity 领域表现很强，但尚未达到 High 级别的网络安全能力。我们预计模型能力仍将快速提升，并很可能在不久的将来跨过 High cybersecurity 的门槛。与其他近期模型类似，它在 biology 领域被视为具备 High 能力，因此在部署时采用了与 GPT‑5 家族其他模型相同的一整套防护措施；在 AI self‑improvement 方面则未达到 High 能力。
----------------------
Introduction
GPT‑5.2-Codex is our most advanced agentic coding model yet for complex, real-world software engineering. A version of GPT‑5.2 optimized for agentic coding in Codex, it includes further improvements on long-horizon work through context compaction, stronger performance on project-scale tasks like refactors and migrations, and improved performance in Windows environments—and significantly stronger cybersecurity capabilities.
This system card outlines the comprehensive safety measures implemented for GPT‑5.2-Codex. It details both model-level mitigations, such as specialized safety training for harmful tasks and prompt injections, and product-level mitigations like agent sandboxing and configurable network access.
GPT‑5.2-Codex was evaluated under our Preparedness Framework. It is very capable in the cybersecurity domain but does not reach High capability on cybersecurity. We expect current trends of rapidly increasing capability to continue, and for models to cross the High cybersecurity threshold in the near future. Like other recent models, it is being treated as High capability on biology, and is being deployed with the corresponding suite of safeguards we use for other models in the GPT‑5 family. It does not reach High capability on AI self-improvement.
via OpenAI News
