AITOPAI热报
Models

Jev 创作者 Diogo Almeida 呼吁开发者用 System One 模型自动化一切

The Jev Revolution: What Engineers Are Already Building with System One Models

Official accountLatent Space (swyx)@Richard MacManus
Blog/Media
Read the original
Why we picked it

Jev 作者 Diogo Almeida 在 Code Summit 上喊话：重复劳动都该自动化，用 System One 模型直接写进工程管线。Glean 已经在生产环境跑了。做工程自动化的开发者可以看看别人怎么接的。

在 AI Engineer Code Summit 上，Jev 的主要创作者 Diogo Almeida 发表演讲，号召开发者将工作流程全面自动化，核心工具是他所称的 System One 模型。System One 模型的思路是把快速、低成本的模型响应当作工程系统的一等构件，让自动化任务不再依赖人工逐步编排。演讲之外，Glean 等公司也在会上展示了他们已在生产环境中使用 Jev 的实际案例。

Body

从会上披露的信息看，Jev 的用法集中在把模型调用嵌入工程管线：企业搜索公司 Glean 展示了如何在自己的产品场景中调用 Jev，说明这类 System One 模型已经开始进入企业级工作流，而不只是开发者玩具。Almeida 的主张是，凡是工程师手动重复做的事情，都可以交给模型自动完成。

与以深度推理为主的 System Two 模型路线相比，Jev 代表的是低延迟、高频调用的另一极，两者在工程中各有分工。对开发者和工程团队而言，这场演讲的意义在于：System One 模型正在从实验性工具变成生产系统中可以直接采用的组件，早接入的团队已经在内部工作流里跑起来了。

Original · Latent Space (swyx)

The Jev Revolution: What Engineers Are Already Building with System One Models

At AI Engineer Code Summit, lead Jev creator Diogo Almeida called on developers to automate everything. Also, Glean and others showed how they’re using Jev.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Jev, Diogo Almeida, Glean, System One 模型.

Source attribution: curated from Latent Space (swyx) (@Richard MacManus).

#Jev#Diogo Almeida#Glean#System One 模型#编程助手

Keep reading

Recent stories with the same tag or section
ModelsBuildersMulti-sourceSelected06:39
Gemini Decision 1 Joins Jev and OpenAI Decision Models

Continuous probability scores instead of hard 1.0/0.0 answers let downstream systems threshold confidence on their own, which matters for media moderation and content-routing pipelines. Engineering teams building video or audio classifiers should benchmark Gemini Decision 1 against OpenAI's GPT-6 Luna, since the two cost the same but differ in modality reach. Budget-sensitive text-only workloads still favour Jev at 4.2 cents per million tokens.

#Gemini#Jev#OpenAI#decision models
Event
Official accountSimon Willison’s WeblogSource
How-toBuildersSelected23:36
Jev passes boost Milvus Vector Graph RAG recall

The result shows cheap small-model passes can beat LLM rerankers when split into selection and ranking stages, cutting model-call latency without losing recall on multi-hop questions. Teams building Graph RAG on Milvus can copy the two-stage pattern directly from the Zilliz repo. Compared with LLM-based reranking, the trade-off is a measurable recall gain for under a second of extra call time.

#Milvus#Jev#RAG#Zilliz
Milvus@milvusioSource