Noam Brown@polynoamial长时运行模型能解决困难的开放式问题，但其持续性可能带来短周期评估未能发现的安全风险。 我们分享了从研究长时运行模型中学到的经验，以及这些发现如何塑造我们在评估、对齐、监控和用户控制方面的策略。 https://openai.com/index/safety-alignment-long-horizon-models/
Long-running models can solve hard open-ended problems， but their persistence can create safety risks that shorter-horizon evaluations miss.
We're sharing what we learned from studying a long-running model， and how those findings are shaping our approach to evaluations， alignment， monitoring， and user control.
https://openai.com/index/safety-alignment-long-horizon-models/
Noam Brown@polynoamial · X长时运行模型能解决困难的开放式问题，但其持续性可能带来短周期评估未能发现的安全风险。 我们分享了从研究长时运行模型中学到的经验，以及这些发现如何塑造我们在评估、对齐、监控和用户控制方面的策略。 https://openai.com/index/safety-alignment-long-horizon-models/
Long-running models can solve hard open-ended problems， but their persistence can create safety risks that shorter-horizon evaluations miss.
We're sharing what we learned from studying a long-running model， and how those findings are shaping our approach to evaluations， alignment， monitoring， and user control.
https://openai.com/index/safety-alignment-long-horizon-models/