X：OpenAI (@OpenAI)· X：OpenAI (@OpenAI)·· 6 天前AI 评分36
OpenAI 谈前沿 RL 训练安全
AI 导读
我们如何看待保障前沿 RL 训练运行的安全：https://openai.com/index/towards-safety-cases-for-frontier-ai-training/
正文
How we think about securing frontier RL training runs: https://openai.com/index/towards-safety-cases-for-frontier-ai-training/
来源：X：OpenAI (@OpenAI) · x.com