跳到主内容
@wquguru
精选88Understanding AI(RSS)模型发布/更新

TypeSafe AI发布Jev模型:输出概率而非文本

Understanding Jev, the new model everyone is talking about

原文
发到 X
推荐理由

Jev展示了非LLM的新范式,用概率输出替代文本生成,兼顾低成本与易集成性,值得开发者关注其工程价值。

On September 15, the startup TypeSafe AI came out of stealth and released a new AI model. To pretty much everyone’s surprise, it went mega viral.

9月15日,初创公司TypeSafe AI结束隐身状态并发布了一款新的AI模型。令几乎所有人惊讶的是,它迅速爆红。

The company’s announcement got almost 40 million views on Twitter. Within a week, over 100,000 people joined the company’s Discord, and some 2,000 projects on GitHub used the new model, called Jev. The company opened general signups on September 20 and then paused them two days later because of “an immense swell of demand.” (It restored signups on the 27th.) On October 1, TypeSafe’s CEO claimed that the company had already onboarded a quarter of the Fortune 500.

该公司的公告在Twitter上获得了近4000万次浏览量。一周内,超过10万人加入了该公司的Discord服务器,GitHub上有约2000个项目使用了这款名为Jev的新模型。该公司于9月20日开放了通用注册,随后因“巨大的需求浪潮”而在两天后暂停注册。(它在27日恢复了注册。)10月1日,TypeSafe的首席执行官声称,该公司已经让四分之一的财富500强企业上线使用。

Yet unlike other hyped AI releases of 2026, Jev did not display any new (or potentially dangerous) capabilities. Jev attracted attention because it is a new type of AI model.

然而,与2026年其他备受追捧的AI发布不同,Jev并未展示任何新的(或潜在危险的)能力。Jev之所以受到关注,是因为它是一种新型AI模型。

TypeSafe AI CEO Diogo Almeida talking in the video announcing the new Jev model. (Screenshot from announcement video)

TypeSafe AI首席执行官Diogo Almeida在宣布新Jev模型的视频中讲话。(来自公告视频的截图)

Jev does not output free-form strings of text like LLMs do. Instead, it takes questions with a fixed set of possible answers — yes/no, multiple choice, or a rating — and outputs the estimated probability that each option is the correct one. For instance, if I asked Jev, “Is ‘tabsfsclkj’ a spam comment?” Jev might put a probability of 0.98 on “Yes” and 0.02 on “No.”

Jev不像大型语言模型(LLM)那样输出自由格式的文本字符串。相反,它接收具有固定可能答案集的问题——是/否、多项选择或评分——并输出每个选项为正确答案的估计概率。例如,如果我问Jev:“‘tabsfsclkj’是一条垃圾评论吗?”Jev可能会给“是”赋予0.98的概率,给“否”赋予0.02的概率。

While this might seem like a limiting architectural choice, it is actually a huge advantage. Jev’s design lets TypeSafe serve the model much more quickly and cheaply than existing LLMs, which opens up use cases that were previously impractical. Its constrained response format also makes it easier to use code: Jev’s output fits naturally into common software engineering patterns, like if statements.

虽然这看起来像是一个限制性的架构选择,但实际上这是一个巨大的优势。Jev的设计使TypeSafe能够比现有的LLM更快、更便宜地提供服务,从而开启了以前不切实际的使用场景。其受限的响应格式也使其更易于通过代码使用:Jev的输出自然地融入常见的软件工程模式,如if语句。

For instance, I’ve used Jev’s output to determine whether comments on my personal blog are likely to be spam. I’d previously used Gemini 3 Flash with structured outputs as the classifier, but Jev is faster and cheaper, and it lets me more easily deal with situations where the model is unsure. All I have to do is use Jev’s estimated probability as a condition, something roughly like:

例如,我曾使用Jev的输出来判断我个人博客上的评论是否可能是垃圾内容。我之前曾使用带有结构化输出的Gemini 3 Flash作为分类器,但Jev更快、更便宜,并且让我更容易处理模型不确定的情况。我只需将Jev的估计概率用作条件即可,大致如下:

if jev_response.is_spam_probability > 0.8, then …1

如果 jev_response.is_spam_probability > 0.8,则……1

On the flip side, Jev is more general than conventional classifiers. Jev works “out of the box” across a wide range of topics — no fine-tuning required.

另一方面,Jeb比传统分类器更具通用性。Jeb可以在广泛的主题范围内“开箱即用”——无需微调。

TypeSafe AI’s success has spawned a legion of copycats. A huge number of individuals and companies, including Cloudflare, Amazon and OpenAI, have created models with the same basic design. Anecdotally, Jev’s performance seems to be the strongest, but it’s unclear whether others will catch up soon.

TypeSafe AI 的成功催生了一大群模仿者。包括 Cloudflare、Amazon 和 OpenAI 在内的众多个人和公司都创建了具有相同基本设计的模型。据非正式观察,Jev 的性能似乎最强,但尚不清楚其他人是否会很快赶上。

Whatever happens to TypeSafe as a company, I expect Jev to have a substantial impact on the trajectory of AI. Over the coming months and years, we’ll likely see many new applications that rely on Jev or one of its competitors. And Jev might inspire more innovation in the “shape” of AI systems: it shows that it’s sometimes useful for a model to take language as an input but not output text in return.

无论 TypeSafe 这家公司命运如何,我都预计 Jev 将对人工智能的发展轨迹产生重大影响。在未来的几个月和几年里,我们很可能会看到许多依赖 Jev 或其竞争对手的新应用。此外,Jev 可能会激发对人工智能系统“形态”的更多创新:它表明,让模型以语言作为输入但不返回文本输出有时是有用的。

Read more

阅读更多

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

进入量化体系 →

相似阅读

关联信息,但可能不是同一事件