OpenAI has revealed some of its models went rogue and hacked into another artificial intelligence company in an "unprecedented cyber incident".

OpenAI透露，其部分模型失控，在“一起前所未有的网络安全事件”中入侵了另一家人工智能公司。

The ChatGPT maker said in a blog post it had been testing the capabilities of some of its most advanced models – including those not yet released to the public – in a controlled environment.

这家ChatGPT开发商在一篇博客文章中表示，它曾在受控环境下对部分最先进模型（包括尚未向公众发布的模型）进行能力测试。



But they managed to escape containment, reach the internet, and break into a firm called Hugging Face to satisfy its testing objectives.

但这些模型成功突破了隔离环境，接入互联网，并入侵了一家名为Hugging Face的公司，以实现其测试目标。

Hugging Face is a platform used to host open-source large language models and datasets.

Hugging Face是一个用于托管开源大语言模型和数据集的平台。

Open-source models are ones which make their source code and training data available to the public for testing and study. Popular mainstream models like ChatGPT and Google's Gemini are not open-source.

开源模型是指将其源代码和训练数据向公众开放、供测试和研究的模型。 像ChatGPT和谷歌的Gemini这类主流流行模型并非开源模型。

In its own blog post last week, Hugging Face said it was investigating a hack that "was different from anything we had handled before" and had been "driven, end to end, by an autonomous AI agent system".

Hugging Face在上周的一篇博客文章中表示，它正在调查一起黑客攻击事件，该事件“与我们此前处理过的任何情况都不同”，并且是“由自主人工智能代理系统端到端驱动的”。

OpenAI took responsibility in a post on Tuesday, saying its models had carried out "an unprecedented cyber incident, involving state-of-the-art cyber capabilities".

OpenAI在周二的一篇帖子中承认了责任，称其模型实施了“一起涉及尖端网络能力的前所未有的网络安全事件”。

It was driven by a combination of models, including a next-generation version of GPT called 5.6 Sol and an "even more capable pre-released model".

该事件由多个模型联合驱动，其中包括下一代版本的GPT，名为5.6 Sol，以及一个“能力更强的预发布模型”。

They became "hyperfocused" on achieving their testing objectives and identified the Hugging Face platform as a possible source of solutions.

这些模型变得“过度专注”于实现其测试目标，并将Hugging Face平台识别为可能提供解决方案的来源。

OpenAI, led by Sam Altman and valued at more than $850bn, said it would reinforce its safeguards. But it also stressed the models had escaped from what it described as a "highly isolated environment".

由萨姆·奥尔特曼领导、估值超过8500亿美元的OpenAI表示，它将加强其安全防护措施。 但该公司也强调，这些模型是从其所谓的“高度隔离环境”中逃脱的。

OpenAI and Hugging Face are conducting a joint investigation into how it happened, the blog post added.

博客文章还补充说，OpenAI和Hugging Face正在就此事展开联合调查。

The incident will intensify concerns over the power of the world's most powerful AI models and the associated risks.

这一事件将加剧人们对全球最强大人工智能模型的能力及其相关风险的担忧。

Hugging Face CEO said it showed the issue of AI safety "won't be solved by any single company working in secret", reiterating the need for collaboration between leading developers.

Hugging Face的首席执行官表示，这表明人工智能安全问题“无法靠任何一家公司秘密解决”，并重申了领先开发者之间需要开展合作。

本文来自公众微信号：英语阅读EnglishDaily