OpenAI 表示已暂停最新部署模型的强化学习（RL）训练两周，期间加固研究环境、开展红队测试并扩大监控覆盖。其规模最大的前沿 RL 训练仍处搁置，等待小规模训练与评测验证安全措施、积累更多对齐证据后再推进。转发该消息的 Testing Catalog 称，OpenAI 是首个宣布暂停训练的 AI 实验室，其他实验室可能跟进。
OpenAI 说明为安全与对齐暂停两周前沿 RL 训练，读者可了解头部实验室推进部署前如何调整训练节奏。
OPENAI 🔥: Frontier RL training has been paused for two weeks in order to meet safety, alignment, and security standards.
So far, OpenAI is the first AI lab to announce a pause in training. Other labs may be expected to follow as well.
> Our largest planned frontier RL run remains on hold while we conduct smaller-scale training and evaluations to assess model behavior, validate our safeguards, and establish more evidence of alignment before proceeding.
That's like pressing the brake before entering a curve.
Exponential takeoff curve, I hope 👀
As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for deployment for two weeks while we hardened and red-teamed our research environments and expanded monitoring coverage. Our largest planned frontier RL run remains on hold while smaller-scale training and evaluations validate these safeguards and establish more evidence of alignment. https://t.co/ecbMMmVoox在 X 查看被引用的帖子
来源：@testingcatalog · x.com