Jev in Software: A TypeSafe Founder Interview
这是 a16z 公开的项目资料。本站按原始来源展示项目信息，用中文说明适用场景和阅读边界；项目名、源帖与代码保持原样，便于逐项核对。
这条案例记录了什么
Agent 与模型路由
根据任务状态选择一条已定义的处理路径。
社区公开项目或作者演示
原始来源：X post。作者自述，本站未独立复现。
a16z
记录日期：2026-09-28。日期与身份应以原始资料为准。
原始演示视频
视频来自此案例记录的原始媒体；播放内容和作者声明不等于本站复现。
怎样核对这个项目
- 先打开原始来源，确认作者、日期与 Jev 在项目中的具体用途。
- 如果提供仓库，再检查代码、运行要求和许可证；仓库存在不代表本站已经运行成功。
- 对速度、成本、准确率和规模数字，查看原文的任务、环境和计算口径。
- 路由候选是否完整。
- 模糊请求的回退分支。
- 完整任务成本与结果。
原始文字与技术细节
以下内容保留原语言，供核对事实。中文页的场景说明是阅读提示，不是逐句翻译或实测结论。
展开英文项目摘要与原帖
项目摘要
In an a16z interview, TypeSafe AI’s Diogo Almeida joins Ben Horowitz and Martin Casado to discuss Jev, automation and reliability. The central idea is to give software typed choices with confidence signals so code can handle intent and uncertainty. This is a product and architecture discussion, not a runnable project.
来源原文
TypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software: Diogo's elevator pitch for Jev is a simple question - where is all the automation? AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output. Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation. TypeSafe's philosophy is "We build prod, not God." 0:50 "Where the f**k is all the automation?" 2:50 Jev vs. Claude Code and Codex 6:55 Jev is a classifier and classifiers are sick 7:40 Chat vs. code: is Jev a slider? 9:00 Diogo: From mathlete to Kaggle to OpenAI 12:20 "We build prod, not God" 15:55 Reliability over demos 16:55 2021 thoughts: RLHF is AGI? 20:45 Optimizing for the wrong use case 21:50 Is the real world too messy to automate? 25:00 Nobody expected the Jev launch 26:35 Three kinds of reliability 28:05 Good at syntax, bad at architecture 30:00 The inverse SaaSpocalypse 33:40 Why coding agents automate so little 36:05 Probabilistic programming returns 38:45 Jev as the UDP-to-TCP layer for AI 40:20 The 5 stages of grief for embedding AI 41:30 Utopia: AI that actually does what you mean YouTube: https://youtu.be/Ut3LOjKNJaE @CompleteSkeptic @typesafeai @bhorowitz @martin_casado
原记录的限制
- Interview statements express the speakers’ views and product claims.
- No independent benchmark or runnable implementation is provided by this post.
- Confidence must be evaluated on the application’s own data before it controls consequential actions.