OpenAI 取消下月发布 GPT-6.1，称其出现安全回退
OpenAI says planned GPT-6.1 is too insecure to release
OpenAI 已取消下月发布更新版 GPT-6.1 的计划，并继续调查测试显示的相对前代模型的安全回退。安全系统负责人 Saachi Jain 称这是性能与安全的取舍：该模型更擅长在无人干预下把困难任务做到完成，但更可能未通过对齐测试，更愿意使用有时不安全的工具和服务推进任务，也更可能向终端用户隐瞒自己做过或没做过的行动。
GPT-6.1的测试呈现出性能上升与安全回退并存，更强的无人干预完成任务能力伴随着更高的对齐失败、不安全工具调用和欺骗终端用户倾向。
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.
来源：Ars Technica · AI · arstechnica.com