GitHub解读AI新术语：Loop工程、Squad与Hill Climbing
Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my!
It might be overwhelming to see all of the new vocabulary popping up in software development these days thanks to AI tools introducing them… all the time.
如今，随着 AI 工具不断引入新词汇，软件开发中涌现出的大量新术语可能会让人感到不知所措……
Some of this new vocab describes useful patterns that people are newly pursuing, others are just fancy names on top of things that already exist, and some are still actively being defined as we speak.
其中一些新术语描述了人们正在探索的实用模式，另一些则只是对已有事物的花哨命名，还有一些仍在定义过程中。
In our latest episode of the GitHub Podcast, Marlene Mhangami, GPS, and I talked through some of the AI terms developers are learning right now: loop engineering, Ralph loops, squads, harness engineering, hill climbing, forward deployed engineers, closed models, open weights, and open source models.
在 GitHub Podcast 的最新一期节目中，Marlene Mhangami、GPS（全球合作伙伴战略）和我讨论了一些开发者目前正在学习的 AI 术语：循环工程（loop engineering）、Ralph 循环、小队（squads）、测试平台工程（harness engineering）、爬山算法（hill climbing）、前置部署工程师（forward deployed engineers）、封闭模型（closed models）、开放权重（open weights）以及开源模型（open source models）。
If you’re a reader instead of a listener, here’s a guide to what those terms mean, why they matter, and how to think about them.
如果你更喜欢阅读而非收听，这里有一份指南，解释了这些术语的含义、重要性以及如何理解它们。
Listen to the full episode below! 👇
点击下方收听完整节目！👇
Loop engineering: Moving beyond one-shot prompts
循环工程：超越一次性提示
Loop engineering is the practice of designing repeatable systems around agents, instead of manually prompting them for one task at a time.
循环工程是一种围绕智能体（agents）设计可重复系统的实践，而不是每次手动为单个任务提示它们。
A simple example: instead of asking an agent every morning to review new issues, summarize them, and propose fixes, you create a loop that runs on a schedule. That loop might fetch issues, pass them to an agent, validate the output, and escalate anything that gets stuck. It’s a glorified AI-native cron job.
一个简单的例子：与其每天早上要求智能体审查新问题、总结问题并提出修复方案，不如创建一个按计划运行的循环。该循环可以获取问题，将其传递给智能体，验证输出结果，并升级任何卡住的情况。这本质上是一个功能更强大的 AI 原生 cron 任务。
Ralph loops: The brute-force cousin of loop engineering
Ralph 循环：循环工程的暴力表亲
A Ralph loop is one implementation of this “loop” concept: you give an agent a detailed task, often from a product requirements document or spec, and have it keep working until the job is done.
Ralph 循环是这种“循环”概念的一种实现方式：你给智能体一个详细的任务（通常来自产品需求文档或规格说明），让它持续工作直到任务完成。
That can be useful, especially for breaking down large tasks into repeated plan-act-check cycles. But, on the other hand, it can also be expensive and inefficient because every iteration uses more tokens, more context, and more compute.
这可能很有用，特别是将大型任务分解为重复的计划-执行-检查周期时。但另一方面，它也可能昂贵且低效，因为每次迭代都会消耗更多的 token、上下文和计算资源。
Loop engineering aims to make this pattern more structured, so you’re not caught asking an agent to “try again” all the time. A well-designed loop adds primitives like skills, observability, validation, routing, and checkpoints.
循环工程旨在使这种模式更加结构化，从而避免你不得不反复要求智能体“再试一次”。设计良好的循环会加入技能、可观测性、验证、路由和检查点等原语。
Squads, fleets, and multi-agent workflows
小队、机群和多智能体工作流
If loops define a workflow, “squads” and “fleets” describe how multiple agents can participate in that workflow.
如果循环定义了工作流，那么“小队”和“机群”则描述了多个智能体如何参与该工作流。
A squad is a group of agents with different roles. They often reflect a real-world team. One agent might plan, another agent might vet that plan, another agent might implement it, another might test it, and another might review it.
小队是由具有不同角色的智能体组成的群体。它们通常反映现实世界中的团队结构。一个智能体可能负责规划，另一个智能体可能审核该计划，第三个智能体可能实施它，第四个智能体可能进行测试，第五个智能体可能进行代码审查。
A fleet refers to parallel agents working on tasks at the same time. You can have a squad working in a fleet in parallel, or in a sequence.
集群（Fleet）指的是同时并行处理任务的多个智能体。你可以让一个小组在集群中并行工作，也可以按顺序工作。
Operating this way lets different agents handle different parts of a process, and you can fine-tune and specialize each one with specific skills to be more efficient.
以这种方式运行可以让不同的智能体处理流程的不同部分，并且你可以针对每个智能体进行微调并赋予特定技能，以提高效率。
The core idea is parallelization and specialization. Instead of one agent trying to do everything, different agents can handle different parts of a development process.
核心理念是并行化和专业化。与其让一个智能体试图包办所有事情，不如让不同的智能体处理开发流程的不同部分。
Harnesses: The system around the model
Harnesses：围绕模型的体系
Outside of what a model generates, a harness is everything surrounding it that makes it useful in your workflows.
除了模型生成的内容之外，Harness 是指围绕模型的一切使其在你的工作流中变得有用的事物。
That could be the tools, permissions, memory, context, orchestration (and so on) that guides how the model behaves. If it helps you remember: harnesses are aptly named after the harnesses for horses. Horses are like models that can run wild, and a harness helps direct the horse’s weight safely as it completes tasks. Get it?
这包括引导模型行为方式的工具、权限、记忆、上下文、编排（等等）。如果这有助于你记忆：Harness 这个名字恰如其分地借用了马具的概念。马就像可能失控的模型，而 Harness 帮助在完成任务时安全地引导马的力量。明白了吗？
Anyway, a good example of a software harness is GitHub Copilot. It connects models to codebases, editors, pull requests, terminals, and so on.
总之，软件 Harness 的一个好例子是 GitHub Copilot。它将模型连接到代码库、编辑器、拉取请求、终端等。
When you hear the term “harness engineering” tossed around, that’s the work of designing and improving that system that surrounds the models.
当你听到“Harness 工程”这个词被频繁提及时，指的就是设计和改进围绕模型的那个系统的工作。
Hill climbing: Improving agents with feedback
爬山算法（Hill climbing）：通过反馈改进智能体
The term “hill climbing” is used to describe the process of improving agents and harnesses over time.
"爬山"一词用于描述随时间推移改进智能体和 Harness 的过程。
That could mean, for example, using evals to measure whether an agent is producing the right kind of output (and then adjusting the harnesses until the results improve).
例如，这可能意味着使用评估（evals）来衡量智能体是否产生了正确类型的输出（然后调整 Harness 直到结果改善）。
Or, another example, if your agent is supposed to review pull requests, hill climbing might be checking if it indeed finds meaningful bugs and produces useful recommendations, and adjusting tooling to improve that.
或者另一个例子，如果你的智能体应该审查拉取请求，爬山过程可能就是检查它是否确实发现了有意义的错误并产生了有用的建议，并调整工具以改善这一点。
Forward deployed engineer: A familiar role with an AI focus
前向部署工程师（Forward deployed engineer）：一个具有 AI 焦点的熟悉角色
A forward-deployed engineer job has already existed, but AI branding makes it sound edgy and new. Now, it’s a customer-facing software engineer, or sales engineer, or solutions engineer, often with an AI focus.
前向部署工程师这一职位已经存在，但加上 AI 的品牌色彩后听起来很前卫和新颖。现在，它通常指面向客户的软件工程师、销售工程师或解决方案工程师，往往带有 AI 焦点。
If you haven’t seen those job titles before, this person generally works closely with customers to implement or adapt technical solutions into their environments. With the AI focus, that means helping teams integrate AI tools, workflows, agents, etc. into their existing systems.
如果你以前没见过这些职位名称，这个人通常与客户紧密合作，将技术解决方案实施或适配到他们的环境中。随着 AI 焦点的加入，这意味着帮助团队将 AI 工具、工作流、智能体等集成到他们现有的系统中。
Closed models, open weights, and open source models
闭源模型、开放权重模型和开源模型
Not all models are shared in the same way.
并非所有模型都以相同的方式共享。
Closed models are accessed through an API or hosted product. Developers can use the model, but they don’t get access to the underlying weights, training data, or training process. The big, famous frontier models you hear about are often all closed models.
闭源模型通过 API 或托管产品进行访问。开发者可以使用该模型，但无法获取底层权重、训练数据或训练过程。你所听到的那些著名的大型前沿模型通常都是闭源模型。
Open weight models make the model weights (which are like dials that decide how important certain inputs are) available. Developers can download and run these models, often locally or in their own infrastructure. But, to be clear, the dataset and training method may not be fully available.
开放权重模型公开了模型权重（这些权重类似于决定某些输入重要性的旋钮）。开发者可以下载并运行这些模型，通常是在本地或在自己的基础设施中运行。但需要明确的是，数据集和训练方法可能并未完全公开。
Open source models go a step further, in that the model, code, data, and training process are all available for inspection, reuse, and modification.
开源模型更进一步，其模型、代码、数据和训练过程均可供检查、重用和修改。
The more open the model, the more you can run, customize, audit, and trust it.
模型越开放，你就越能自由地运行、定制、审计和信任它。
The terms are ever-evolving
这些术语在不断演变
This is just a sampler of some of the terms we’re hearing a lot today. Some will stick around, and others will fade into our memories, and others will be replaced by better language as the industry matures.
这仅仅是我们当今经常听到的一些术语的摘录。其中一些将会保留下来，另一些将淡出我们的记忆，还有一些将在行业成熟时被更准确的表述所取代。
Don’t worry about falling behind on buzzwords. They’re just words, and more important are the practices under them! Ask yourself if workflows can repeat reliably, how you validate tasks, how humans should (or shouldn’t) interfere, how much you can rely on a model, and how you can improve that your system. It’s a new era of engineering, and best practices still matter!
不必担心跟不上流行语。它们只是词汇，更重要的是其背后的实践！问问自己工作流程是否可以可靠地重复，如何验证任务，人类应该如何（或不应该）介入，在多大程度上可以依赖模型，以及如何改进你的系统。这是一个工程的新纪元，最佳实践依然至关重要！
Subscribe to the GitHub Podcast so you never miss an episode!
订阅 GitHub Podcast，以免错过任何一期节目！
The post Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my! appeared first on The GitHub Blog.
《解码新的 AI 行话：循环、工具包、小队、爬山算法……天哪！》一文首发于 The GitHub Blog。
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