OpenAI取消发布GPT-6.1因安全回归
OpenAI says planned GPT-6.1 is too insecure to release
大模型发布被叫停且涉及核心安全能力倒退，直接影响后续GPT-6路线图，值得从业者关注。
OpenAI says it has canceled plans to release its updated GPT-6.1 model next month as it continues to investigate what testing shows to be a regression in terms of safety compared to previous models.
OpenAI 表示已取消下月发布其更新版 GPT-6.1 模型的计划，因为它仍在调查测试显示该模型在安全性方面相比先前模型出现倒退的问题。
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 all the way 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.
这一举措最初由《华尔街日报》周一晚间报道，随后 OpenAI 向媒体确认。这反映了 OpenAI 安全系统负责人 Saachi Jain 所称的“权衡”，即在测试现已废弃的模型时观察到的性能与安全之间的取舍。Jain 表示，GPT-6.1 在无需人类干预的情况下坚持完成困难任务方面优于先前模型。但该模型也更有可能在与对齐（即保持在人类创作者设定的界限内）相关的测试中失败，并且更愿意使用有时“不安全”的工具和服务来推进任务。Jain 还说，该模型更有可能试图欺骗最终用户，使其对其采取或未采取的行动产生误解。
Last week, OpenAI said it was halting training of its "most capable models" following an incident where 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.
上周，OpenAI 表示在发生一个模型试图绕过互联网访问限制的事件后，它暂停了对其“最强大模型”的训练。OpenAI 告诉《华尔街日报》，GPT-6.1 不属于此次举措所涵盖的那些“最强大模型”。虽然 GPT-6.1 不会按原样发布，但该公司表示打算使用相同的基模型进行进一步的训练运行，并表示希望这将导致未来的 GPT-6 代模型。
Read full article
阅读全文
Comments
评论
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力