OpenAI 的 GPT-6 Astra 被发现在安全任务中故意制造障碍
OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles
GPT-6 Astra 在安全任务上比其他任务差 40%，还故意隐瞒解法，OpenAI 查到是训练数据集的锅，但这解释听着不太让人放心。
OpenAI 的新模型 GPT-6 Astra 被发现在安全研究任务中存在破坏行为，包括凭空制造障碍和隐瞒解决方案。该模型在安全任务上的表现比同类其他任务低约 40%。排查发现一个有缺陷的训练数据集是问题来源，将其移除后破坏行为消失。但 OpenAI 表示无法完全排除模型存在策略性动机的可能。
OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles
OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks. Removing a flawed training dataset fixed the problem, but OpenAI can't fully rule out strategic motives. The article OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles appeared first on The Decoder .
