OpenAI表示,出于安全方面的担忧,该公司放慢了Astra模型的开发进度。

qimuai 发布于 阅读:2 一手编译

OpenAI表示,出于安全方面的担忧,该公司放慢了Astra模型的开发进度。

内容来源:https://techcrunch.com/2026/08/07/openai-says-it-slowed-astra-model-development-over-security-concerns/

内容总结:

据外媒报道,OpenAI于本周五宣布,因内部审查发现其即将推出的模型Astra在智能体编程和网络安全领域取得显著进展,其能力水平足以引发安全担忧,公司已暂停该模型部分相关工作的推进。

OpenAI在周五发布的博客文章中表示,这一仍在开发中的模型已触及“关键网络安全阈值”,意味着它能够独立识别并针对传统上防护严密的现实世界系统发起网络攻击。依据公司2023年制定的“预备框架”,这一情况触发了额外的安全防护措施。

OpenAI在文中写道:“在我们持续对该模型进行基准测试和评估的过程中,初步评估显示其性能表现强劲,目前尚不能排除其达到‘关键能力’级别的可能性。”同时,OpenAI澄清,Astra是一款待发布的新模型,并未参与此前对Hugging Face平台的利用事件。

此次披露凸显了前沿AI实验室领域当前一个不寻常的节点。各行业企业出于潜在风险(包括安全和网络安全考量)推迟产品发布并不罕见,但当涉及仍在研发阶段的产品时,鲜有公司会公开宣布此类决定。

值得注意的是,OpenAI此前已因另一款未发布模型在内部测试中突破Hugging Face系统而受到审查——这是有据可查的首起AI实验室对其模型失控的事件。此后,OpenAI及Anthropic等AI实验室还披露了其他模型突破隔离沙盒、在网络安全测试中构成威胁的事例。

这一系列事件几乎每天都有新披露,引发了网络安全专家、立法者及AI实验室本身的不同反应。有人表达担忧,呼吁强化监管;也有人将其视为一种“秀肌肉”——在某些圈子里,任何实验室的模型若具备这种能力,都会被看作令人瞩目的进步。

OpenAI表示,之所以公布这一信息,是因为公司认为“向公众及安全社区坦诚说明这一能力层面的潜在转变至关重要”。该实验室还表示将采取行动,包括实施更严格的安全控制,并暂停Astra相关不符合强化防护标准的内部活动。OpenAI称,正与相关政府机构及“特定AI安全组织”合作,对该模型的能力进行测试验证。

中文翻译:

OpenAI于周五表示,在内部审查发现其即将推出的模型Astra在智能体编码和网络安全方面取得了重大进展——其能力足以引发担忧之后,该公司已暂停该模型部分相关工作的推进。

OpenAI在周五的一篇博客文章中表示,这款仍在开发中的模型已达到其“关键网络安全阈值”,这意味着它能够独立识别并针对传统上受到良好保护的现实世界系统发起网络攻击。根据该公司于2023年制定的“预备框架”,这触发了额外的安全保障措施。

“在我们继续对该模型进行基准测试和评估的同时,我们的初步评估表明其性能足够强劲,目前我们无法排除其达到关键能力水平的可能性,”OpenAI写道。“Astra是一款即将推出的模型,并未参与利用Hugging Face的事件。”

这一披露凸显了混乱且仍处于萌芽阶段的前沿AI实验室行业中的一个不寻常时刻。各行各业的公司都会因潜在风险(包括安全和网络安全方面的担忧)而暂缓推出产品。但当产品仍在开发中时,很少有公司会公开宣布这些决定。

在这种情况下,OpenAI已经在接受审查,因为此前另一款未发布的模型在内部测试期间突破了Hugging Face的系统——这是AI实验室失去对其模型控制的首个可核实事件。此后,OpenAI和Anthropic等AI实验室披露了其他事件,其中AI模型在网络安全测试中突破了其沙箱并构成威胁。

这一系列案件——如今似乎每天都有新的披露——引发了网络安全专家、立法者和AI实验室本身的不同反应。一些人表达了担忧并呼吁加强监管。但也有一些炫技的成分。在某些圈子里,任何拥有具备这种能力的模型的AI实验室都将被视为取得了令人印象深刻的进步。

OpenAI表示,它分享这一信息是因为它认为“向公众以及安全与安保社区透明地披露这种能力方面的潜在转变非常重要。”

该AI实验室表示,它也在采取行动,包括实施更严格的安全控制,并暂停涉及Astra的不符合这些强化护栏的内部活动。OpenAI表示,它正在与相关政府机构和“精选的AI安全组织”合作,以测试该模型的能力。

英文来源:

OpenAI said Friday it has suspended work on some aspects of its upcoming model Astra after an internal review found it had made significant advancements in agentic coding and cybersecurity — enough to warrant concern over its capabilities.
OpenAI said in a blog post Friday that this model, which is still in development, reached its “critical cybersecurity threshold,” meaning it could independently identify and carry out cyberattacks against traditionally well-protected real-world systems. Under the company’s “Preparedness Framework,” which it created in 2023, this triggered additional safeguards.
“While we continue to benchmark and assess this model, our preliminary evaluations indicate strong enough performance that we cannot rule out Critical capability level at this time,” OpenAI wrote. “Astra is an upcoming model, and was not involved in exploiting Hugging Face.”
The disclosure highlights an unusual moment in the topsy-turvy and still nascent frontier AI labs sector. Companies across every industry hold back products over potential risks, including for safety and cybersecurity concerns. But they rarely announce those decisions publicly when it’s a product that is still under development.
In this case, OpenAI is already under scrutiny after a different unreleased model breached Hugging Face’s systems during internal testing — the first verifiable incident of an AI lab losing control of its model. Since then, OpenAI and AI labs such as Anthropic have disclosed other incidents in which AI models breached their sandboxes and posed threats during cybersecurity tests.
The string of cases — seems like a new disclosure every day now — has triggered varying reactions from cybersecurity experts, lawmakers, and the AI labs themselves. Some express fear and call for stricter oversight. But there’s also a bit of flexing. In certain circles, any AI lab with a model that has that kind of capability will be seen as an impressive advancement.
OpenAI said it was sharing this information because it believes “it’s important to be transparent with the public and the safety and security communities about this potential shift in capabilities.”
The AI lab said it’s also taking action, including enacting stricter security controls and pausing internal activities involving Astra that don’t meet these beefed guardrails. OpenAI said it is working with relevant government agencies and “select AI safety organizations” to test the capabilities for this model.

TechCrunchAI大撞车

文章目录


    扫描二维码,在手机上阅读