HackerNews中文版

标题：JSE – 一种基于JSON的S表达式格式，用于结构化AI输出大家好，我一直在尝试一个关于AI系统结构化输出的小想法，想分享一个早期的规范以获取反馈。 *JSE（JSON结构表达式）* 是一种轻量级约定，允许 *S表达式风格的逻辑嵌入有效的JSON中*。动机很简单：现代AI模型能够可靠地生成JSON。然而，JSON通常被视为*数据*，而许多AI交互实际上需要表达*结构化意图或计算*（类似于Lisp表达式、DSL或AST）。工具调用和MCP解决了一部分问题，但它们往往是*特定于API的协议*，而不是*通用的结构表示*。 JSE试图用最小的规则集填补这一空白。 --- ### 核心思想在JSE中： * 以`$`开头的字符串被视为*符号* * JSON数组或对象可以表示*S表达式* * 格式保持*100%有效的JSON* * 元数据可以与表达式共存 * `$quote`允许原始数据部分从概念上讲： > 就像一个*组*由*集合加上定义在其上的操作*组成， > *JSE是应用于JSON数据的S表达式系统。* 示例： ```json ["$add", 1, 2] ``` 或者带有元数据： ```json { "$call": "$search", "query": "JSON S-expression", "top_k": 5 } ``` 理解JSE的系统可以将这些视为结构化操作，而不理解的系统仍然可以将其视为普通的JSON。 --- ### 这对AI可能有用的原因许多AI系统需要传达诸如： * 推理计划 * 工具管道 * 结构化转换 * 查询语言 * 类DSL指令如今，这些通常实现为： * 特定的JSON模式 * 工具特定格式 * 嵌入的代码字符串 JSE试图提供一种*结构化意图的统一表示*，其特点是： * 确定性 * 机器可解释 * 易于LLM生成 * 易于人类阅读重要的是，*JSE并不旨在成为一个完整的Lisp或图灵完备的系统*。每个实现可以选择支持多少表达空间。 --- ### 设计约束该格式试图满足一些实际目标： * 始终有效的JSON * 易于LLM生成 * 接近S表达式语义 * 可扩展的元数据 * 足够轻量以嵌入提示或API响应中 --- ### 示例用例一些可能有用的领域： * AI编排系统 * 代理通信协议 * 结构化推理跟踪 * 嵌入式DSL提示 * 跨模型通信格式 --- ### 规范和代码库早期规范和示例在这里： https://github.com/MarchLiu/jse 该规范有意设计为可以*直接嵌入提示中*，允许模型一致地生成JSE结构。 --- ### 我希望获得反馈的问题 * 是否有我应该研究的先前作品？ * 与JSON Schema / 工具调用相比，这是否有用？ * `$symbol`的设计是否合理？ * 在语义上是否存在明显的边缘案例？期待听到大家的想法。

查看原文

Title: JSE – A JSON-based S-Expression format for structured AI outputsHi HN,I’ve been experimenting with a small idea around structured outputs for AI systems and wanted to share an early spec to get feedback.*JSE (JSON Structural Expression)* is a lightweight convention that allows *S-expression style logic to be encoded inside valid JSON*.The motivation is simple:Modern AI models can reliably generate JSON. However, JSON is usually treated purely as *data*, while many AI interactions actually need to express *structured intent or computation* (similar to Lisp expressions, DSLs, or ASTs).Tool calls and MCP solve some of this, but they tend to be *API-specific protocols* rather than a *general structural representation*.JSE tries to fill that gap with a minimal rule set.---### Core ideaIn JSE:* Strings starting with `$` are treated as *symbols* * JSON arrays or objects can represent *S-expressions* * The format remains *100% valid JSON* * Metadata can coexist with expressions * `$quote` allows raw data sectionsConceptually:> Just as a *group* consists of a *set plus operations defined on it*, > *JSE is an S-expression system applied to JSON data.*Example:```json ["$add", 1, 2] ```Or with metadata:```json { "$call": "$search", "query": "JSON S-expression", "top_k": 5 } ```A system that understands JSE can interpret these as structured operations, while systems that don’t can still treat them as ordinary JSON.---### Why this might be useful for AIMany AI systems need to communicate things like:* reasoning plans * tool pipelines * structured transformations * query languages * DSL-like instructionsToday these are usually implemented as:* ad-hoc JSON schemas * tool-specific formats * embedded code stringsJSE attempts to provide a *uniform representation for structured intent* that is:* deterministic * machine interpretable * easy for LLMs to generate * easy for humans to readImportantly, *JSE does not aim to be a full Lisp or a Turing-complete system*. Each implementation can choose how much of the expression space it supports.---### Design constraintsThe format tries to satisfy a few practical goals:* Always valid JSON * Easy for LLMs to generate * Close to S-expression semantics * Extensible for metadata * Lightweight enough to embed in prompts or API responses---### Example use casesSome areas where this might be useful:AI orchestration systems Agent communication protocols Structured reasoning traces Prompt-embedded DSLs Cross-model communication formats---### Spec and repoEarly spec and examples are here:https://github.com/MarchLiu/jseThe spec is intentionally designed so it can also be *embedded directly inside prompts*, allowing models to generate JSE structures consistently.---### Questions I’d love feedback on* Is there prior art I should study? * Would this be useful compared to JSON Schema / tool calling? * Does the `$symbol` design feel reasonable? * Are there obvious edge cases in the semantics?Curious to hear thoughts.

JSE：人工智能代理的结构化表达协议