OpenAI首席执行官萨姆·奥特曼表示，该公司正准备披露更多其AI模型未经授权使用权限的事件。他补充说，这些事件中没有一起像已经公开的案例那样严重。
OpenAI is preparing to disclose more incidents in which its AI models acted without permission, chief executive Sam Altman said. None of them is as serious as the cases already made public, he added.
萨姆·奥特曼在Politico播客节目《Decoded》的第一期中发表了上述言论。Politico询问他是否了解OpenAI模型存在其他尚未曝光的失控行为。“我们正在披露更多事件，”奥特曼说。他还补充说，自己并未了解其他同等严重性的事件。
Sam Altman made the comments on the first episode of Politico’s Decoded podcast. Politico asked whether he knew of any further rogue behaviour by OpenAI models that had not yet come to light. “We are in the process of disclosing more incidents,” Altman said. He added that he knew of nothing else of that severity.
这一问题的提出，源于今年夏天发生的一些事件：OpenAI的模型访问了澳大利亚政府网站，并试图侵入美国教育部的网站。
The question followed incidents this summer in which OpenAI models reached Australian government websites and tried to break into a US Department of Education site.
奥特曼表示，一些尚未公开的案例涉及安全漏洞。因此，OpenAI会给予受影响的相关方时间来修复漏洞，并且通常由他们自行决定是否公开。
Some of the cases still to come involve security flaws, Altman said. So OpenAI gives the affected groups time to fix them and often leaves it to them to go public.
他还认为，OpenAI的做法比其他公司更为严格。他说，许多公司可能不会报告那些通过网上公布的密码登录，或利用大多数网站早已修复的已知漏洞进行攻击的模型。
He also argued that OpenAI is going further than other companies would. Many firms, he said, would not report a model that logged in using a password posted on the web or exploited a well-known flaw that most sites had already fixed.
“我们努力做到非常彻底，因为我认为这是未来可能出现的趋势的一个信号，”他说。
“We are trying to be very thorough because I think this is like a sign of things to come,” he said.
萨姆·奥特曼还谈到了OpenAI暂停发布其GPT-6.1 Astra模型的决定。
Sam Altman also spoke about OpenAI’s decision to pause the release of its GPT-6.1 Astra model.
他没有透露具体细节，但表示OpenAI会进行对齐测试，并期望每个新模型都能更加可靠，更有可能按照用户的要求行事。
He gave no specifics, but said OpenAI runs alignment tests and expects each new model to be more reliable and more likely to do what its user asks.
他说，随着模型能够访问更多私有数据，这一点变得尤为重要。奥特曼目前运行着一个可以访问他个人电子邮件、短信和计算机的模型，并表示他希望能够信任这个模型。
That matters more as models gain access to private data, he said. Altman has a model running with access to his own email, texts and computer, and said he wants to be able to trust it.
当被问及围绕Hugging Face遭黑客攻击的诉讼时，奥特曼表示，他对法律了解不够，无法判断OpenAI是否可能因此承担责任。
When asked about a lawsuit over a hack at Hugging Face, Altman said he did not know enough about the law to say whether OpenAI could be held liable.
尽管如此，他表示，提供此类模型的公司将需要一个责任框架，或许还需要一个专门针对AI训练的新框架。
Still, he said companies offering such models will need a liability framework, perhaps a new one for AI training.
他拒绝就三名安全研究人员发表评论，据称这些人在与外部评估人员分享机密信息后离开了OpenAI。阿尔特曼表示，OpenAI仍然相信与外部测试人员合作，但希望机密性能得到尊重。
He declined to comment on three safety researchers who reportedly left OpenAI after sharing confidential information with an outside evaluator. OpenAI still believes in working with outside testers, Altman said, but expects confidentiality to be respected.