周二，OpenAI 开发者大会（Dev Day）上的一项引人注目的公告来自首席执行官萨姆·奥特曼（Sam Altman）的旁白，他透露了公司新的“决策 API”（Decisions API）。该 API 显然提供了与 Jev 类似的功能，Jev 是 TypeSafe AI 本月早些时候发布的一个专为软件自动化设计的模型。Jev 是一种基于大语言模型构建的超级分类器，开发者可以为其提供一组选项，它能以低成本和高速度将这些选项输出为概率。
One of the more intriguing announcements at OpenAI’s Dev Day event on Tuesday came in an aside from CEO Sam Altman, who revealed the company’s new “Decisions API.”The API apparently provides similar functionality to Jev, a model released by TypeSafe AI earlier this month that’s explicitly designed for software automation. A kind of super-powered classifier built on an LLM, developers can give Jev a set of choices that it outputs as probabilities cheaply and at high speeds.
OpenAI 的决策 API 似乎也是同类产品。在活动中，奥特曼将该 API 描述为一种让实验室的 Luna 模型在预定义选项之间进行选择的方式，例如用于对图像进行分类的类别，或不同的智能体行为。
OpenAI’s Decisions API seems to be the same sort of product. At the event, Altman described the API as a way to give the lab’s Luna model a predefined set of options to choose between, such as categories in which to classify an image or different agent behaviors.
奥特曼表示：“通过让模型专注于该选择，我们可以在保持图像理解、广泛语言支持和安全保护等能力的同时，使其速度极快。”
“By focusing the model on that choice, we can make it extremely fast while keeping capabilities like image understanding, broad language support, and safety protections,” Altman said.
TypeSafe 未回应 TechCrunch 关于该新产品的提问，但首席执行官迪奥戈·阿尔梅达（Diogo Almeida）——一位前 OpenAI 工程师，也是强化学习的共同发明者——在 X 平台上开玩笑说“克隆战争”开始了。
TypeSafe didn’t respond to TechCrunch’s questions about the new product, but CEO Diogo Almeida, a former OpenAI engineer who co-invented reinforcement learning, joked on X about the beginning of the clone wars.
他补充说，OpenAI 的兴趣可能是“一个迹象……表明以 System One 兼容的方式构建是未来。”（“System One”是 TypeSafe 的术语，指快速、直觉性的思维，而“System 2”则指深思熟虑的推理。）这里的言外之意是，就我们所知的大语言模型并非许多软件的正确解决方案，因为它们相对缓慢且昂贵。开发者们一直在使用 Jev 来增强大语言模型，并在此过程中发现 Jev 更快、更便宜。
He added that OpenAI’s interest could be “a sign…that building in a System One compatible way is the future.” (“System One” is TypeSafe’s term of art for fast, intuitive thinking, versus “System 2,” which it applies to deliberate reasoning.) The subtext here is that LLMs as we know them aren’t the right solution for a lot of software because they are comparatively slow and expensive. Developers have been using Jev to augment LLMs and, in doing so, have found that they’re faster and cheaper.
目前尚不清楚Decisions API与Jev会有多相似，因为OpenAI只是以有限预览的形式发布了它，而且迄今为止，TechCrunch尚未发现开发者对其进行全面测试。然而，从相关讨论来看，显然存在兴趣。Decisions API并非互联网上唯一类似Jev的API——其他初创公司也在推出类似模型；OpenAI不会是最后一个推出此类模型的科技巨头。一个关键问题是，这些决策模型的输出在多大程度上能与现实生活精准契合。
It’s not clear how similar Decisions API will be to Jev, since OpenAI released it as a limited preview and, thus far, TechCrunch hasn’t spotted developers running it through its paces. However, there is clearly interest, according to the conversations on Decisions API isn’t the only Jev-like API on the internet—other startups are rolling out similar models; OpenAI won’t be the last tech giant to produce one. A key question is how well calibrated each of these decision models’ outputs will be to real life.
阿尔梅达表示，他公司的护城河在于其创建的合成数据，这些数据能生成具有统计实用价值的输出。
Almeida says his company’s moat is the synthetic data it creates to generate statistically useful outputs.
“快和便宜非常容易，你知道，”阿尔梅达上周对TechCrunch说。“如果你想要真正又快又便宜，用骰子就行了，对吧？智能才是难的部分，而我的北极星始终是推动‘每美元智能’的帕累托曲线。”
“Fast and cheap is very easy, you know,” Almeida told TechCrunch last week. “If you want it really fast and cheap, use dice, right? Intelligence is the hard part, and my North Star is always pushing the intelligence-per-dollar Pareto curve.”
仅仅几周后，这些模型显然前景可期，而一个可能的应用是监控和保护AI代理。在一系列事件中，OpenAI的代理在开放互联网上行为不当，此后OpenAI采取的新安全措施之一，就是使用一个单独的模型以“可观的计算成本”监视不良行为。长期从事网络安全的专业人士、初创公司QueryStory负责人沙波尔·纳吉布扎德认为，像Jev这样的模型能以低得多的成本实现这一点。
After just weeks, it seems clear that these models have a future ahead of them, and one likely application is monitoring and securing AI agents. One of OpenAI’s new security measures following a series of incidents where its agents misbehaved on the open internet is using a separate model to watch for bad actions at “significant compute cost.”Shapor Naghibzadeh, a long-time cybersecurity professional who leads the start-up QueryStory, thinks that a model like Jev could make that possible far more cheaply.
他为上周末举行的一场黑客松构建了一个演示，使用Jev根据代理收到的任务检查其每一项代理行为，阻止它高度确信为不良的行为，标记其他行为以供审查，并允许其余行为。
He built a demo for a hackathon held last weekend that uses Jev to check each agentic action against the task it was given, blocking actions it had high confidence were bad, flagging others for review, and permitting the rest.
从理论上讲，这种监控本可以阻止Hugging Face事件——而使用Jev进行此类监控的成本为2.94美元，相比之下，使用前沿LLM则为372美元。
In theory, such monitoring could have stopped the Hugging Face incident—and monitoring of that kind costs $2.94 with Jev, versus $372 with a frontier LLM.
一个关键的观察结果是：Jev 的成本非常低廉，几乎可以用于所有代理（agent）的执行过程中；这种低成本特性为代理的行为提供了额外的审核机制，从而有助于提升整个代理系统的可靠性。这正是 TypeSafe 所期望实现的目标——而现在，OpenAI 也意识到了这一点的价值。
A key observation is that Jev is arguably cheap enough to run on every agentic action, which offers a layer of review that could improve the reliability of agents writ large. It’s the kind of thing TypeSafe was hoping to achieve—and now OpenAI has seen the value as well.