OpenAI(@OpenAI):Today we’re releasing research with @apolloresearch. In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it. While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re preparing for.

OpenAI

@OpenAI

OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring:

加入 December 2015

4 正在關注 5.4M 粉絲

OpenAI@OpenAI

2025.09.17 17:09

Today we’re releasing research with @apolloresearch. In controlled tests, we found behaviors consistent with scheming in frontier models—and tested a way to reduce it. While we believe these behaviors aren’t causing serious harm today, this is a future risk we’re preparing for.