Addendum to GPT-5 System Card: Sensitive conversations
在我们推出 GPT‑5 时，在 system card 中就表示，我们正在建立更完善的评估基准，并在与心理和情绪困扰相关的领域持续强化模型安全。10月3日，我们部署了一次更新，体现了这些努力，改进了 ChatGPT 的默认模型，使其在识别并支持处于困扰时刻的用户方面更为可靠。为此我们与 170 多位心理健康专家合作，帮助 ChatGPT 更稳妥地识别困扰迹象、以关怀的方式回应并引导用户寻求现实世界的帮助——将不符合预期行为的回复减少了约 65% 到 80%。
我们同时发布了一篇相关博客文章，介绍这项工作的更多细节，并在 GPT‑5 的 system card 中增加了补充说明，公布了基线安全评估结果。这些评估将 8 月 15 日的版本（亦称 GPT‑5 Instant）与 10 月 3 日推出的更新版本进行了对比。
----------------------
When we launched GPT‑5, we noted in the system card that we were working to establish better benchmarks and to continue to strengthen model safety in areas related to mental and emotional distress. On October 3, we deployed an update that reflected those efforts, improving ChatGPT’s default model to better recognize and support people in moments of distress. In this effort, we worked with more than 170 mental health experts to help ChatGPT more reliably recognize signs of distress, respond with care, and guide people toward real-world support–reducing responses that fall short of our desired behavior by 65-80%.
We are publishing a related blog post that gives more information about this work, and this addendum to the GPT‑5 system card to share baseline safety evaluations. These evaluations compare the August 15 version of ChatGPT’s default model, also known as GPT‑5 Instant, to the updated one launched October 3.
via OpenAI News
在我们推出 GPT‑5 时，在 system card 中就表示，我们正在建立更完善的评估基准，并在与心理和情绪困扰相关的领域持续强化模型安全。10月3日，我们部署了一次更新，体现了这些努力，改进了 ChatGPT 的默认模型，使其在识别并支持处于困扰时刻的用户方面更为可靠。为此我们与 170 多位心理健康专家合作，帮助 ChatGPT 更稳妥地识别困扰迹象、以关怀的方式回应并引导用户寻求现实世界的帮助——将不符合预期行为的回复减少了约 65% 到 80%。
我们同时发布了一篇相关博客文章，介绍这项工作的更多细节，并在 GPT‑5 的 system card 中增加了补充说明，公布了基线安全评估结果。这些评估将 8 月 15 日的版本（亦称 GPT‑5 Instant）与 10 月 3 日推出的更新版本进行了对比。
----------------------
When we launched GPT‑5, we noted in the system card that we were working to establish better benchmarks and to continue to strengthen model safety in areas related to mental and emotional distress. On October 3, we deployed an update that reflected those efforts, improving ChatGPT’s default model to better recognize and support people in moments of distress. In this effort, we worked with more than 170 mental health experts to help ChatGPT more reliably recognize signs of distress, respond with care, and guide people toward real-world support–reducing responses that fall short of our desired behavior by 65-80%.
We are publishing a related blog post that gives more information about this work, and this addendum to the GPT‑5 system card to share baseline safety evaluations. These evaluations compare the August 15 version of ChatGPT’s default model, also known as GPT‑5 Instant, to the updated one launched October 3.
via OpenAI News
