OpenAI研究：训练广泛持久有益的模型

OpenAI@OpenAI

2026-06-19 05:34·2天前

AI 摘要

随着AI承担更长时间、更高风险的任务，我们希望模型能将有益且安全的行为带入训练之外的新领域——并在压力下保持这种行为。这正是我们关于训练模型实现广泛且持久有益的新研究背后的理念。https://alignment.openai.com/beneficial-rl/

As AI takes on longer， higher-stakes tasks， we want models to carry beneficial and safe behavior into new domains beyond their training-and maintain it under pressure.

That's the idea behind our new research on training models to be broadly and persistently beneficial. https：//alignment.openai.com/beneficial-rl/

OpenAI安全/对齐论文/研究

在 X 查看原推

OpenAI@OpenAI · X

2026-06-19 05:34·2天前

AI 摘要

As AI takes on longer， higher-stakes tasks， we want models to carry beneficial and safe behavior into new domains beyond their training-and maintain it under pressure.

That's the idea behind our new research on training models to be broadly and persistently beneficial. https：//alignment.openai.com/beneficial-rl/

OpenAI安全/对齐论文/研究

在 X 查看原推x.com