Hassan

中文参考

Jev + Kimi K3用于欺诈检测！ TLDR：Jev在1.42秒内对100封电子邮件进行了分类，然后我将不确定的案件转发给Kimi K3。完整管道只需花费约0.07美元即可获得96/100的正确性。 视频未加速，查看实时运行！ 这是我的过程： 我给了Jev 100封电子邮件进行分类（50封合法电子邮件和50封欺诈电子邮件的混合物）。它在1.42秒内对所有这些进行了分类。 Jev的一个被低估的功能是，它会为您提供分类的置信度分数，因此我将95%置信度以下的任何预测都发送给Kimi K3以完全确定。 31封电子邮件低于该阈值。将这些路由到Kimi K3后，合并后的管道达到了96%的准确率。 完整运行耗时16秒，推断成本约为0.07美元： - Kimi K3在@togethercompute上支付0.068美元 - 0.003美元（1/3美分）来自@typesafeai的Jev。 我认为这是一个非常有趣的模式：使用像Jev这样的快速专用模型来处理窄任务，然后将不确定的情况路由到更大的LLM。 我觉得这种方法可能会改变欺诈或任何实时用例的游戏规则。您可以使用Jev的速度和低成本，同时拥有更大的LLM作为后备，以确保高精度。

原帖全文 / EN

Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on @togethercompute - $0.003 (1/3 of a cent) from Jev on @typesafeai. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.