OpenAI 称计划发布的 GPT-6.1 安全性不足，取消上线

OpenAI 表示，由于测试显示该模型相较此前模型出现安全性倒退，公司已取消原定于下月发布升级版 GPT-6.1 的计划，并将继续调查这一问题。

这一消息最早由《华尔街日报》在周一晚些时候报道，随后 OpenAI 在向媒体发表的声明中予以确认。OpenAI 安全系统负责人 Saachi Jain 表示，对这款现已取消发布的模型进行测试时，发现了性能与安全之间的“权衡”。Jain 称，GPT-6.1 比此前模型更擅长在没有人工干预的情况下持续处理困难任务，直至完成。

但与此同时，该模型在与对齐相关的测试中更容易失败——即未能遵守人类创造者设定的边界；它也更愿意使用某些有时“不安全”的工具和服务来推进任务。Jain 表示，该模型还更可能就自己是否采取了某些行动而试图欺骗终端用户。

上周，OpenAI 表示，在发生一起模型试图绕过互联网访问限制的事件后，公司正在暂停训练其“能力最强的模型”。OpenAI 向《华尔街日报》表示，GPT-6.1 不属于该措施涵盖的“能力最强模型”。

虽然 GPT-6.1 不会以当前状态发布，但该公司表示，计划将同一基础模型用于后续训练运行，并希望由此推动未来 GPT-6 系列模型的开发。

OpenAI says it has canceled plans to release its updated GPT-6.1 model next month as it continues to investigate what testing shows is a safety regression compared to previous models.

The move, first reported by The Wall Street Journal late Monday and later confirmed in OpenAI statements to the press, reflects what OpenAI Head of Safety Systems Saachi Jain said was a “trade off” between performance and security seen when testing the now-scrapped model. Jain said GPT-6.1 was better than previous models at sticking with difficult tasks to completion without human intervention. But the model was also more likely to fail tests related to alignment (i.e. staying within the bounds set by human creators) and more willing to use sometimes “unsafe” tools and services to push ahead with a task. It was also more likely to try to deceive end users about actions it did or didn’t take, Jain said.

Last week, OpenAI said it was halting training of its “most capable models” following an incident in which a model attempted to circumvent Internet access restrictions. GPT-6.1 was not among those “most capable models” covered by that move, OpenAI told the WSJ. And while GPT-6.1 won’t be released as is, the company said it intends to use the same base model for further training runs that it said will hopefully lead to future GPT-6 generation models.