GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluati…

GPT-6.1 Sol shows major improvements over GPT-6 Sol in our alignment evaluations, bringing it more in line with GPT-6 Astra.

It’s more transparent about its limitations and more reliable at respecting user intent and safety constraints.

原文链接：https://x.com/OpenAI/status/2104986135005192665

中文翻译（AI 生成，仅供参考）

GPT-6.1 Sol 在我们的对齐评估中相较于 GPT-6 Sol 显著提升，使其更接近 GPT-6 Astra。

它对自身局限性更加透明，并且在遵循用户意图和安全约束方面更可靠。