官方更新 GitHub Blog AI/ML Fri, 02 Oct 2026 正文 ok 571 words

AI 正在改变开发者工作:需要强化的三项技能

英文标题:AI is changing developer work. Here are three skills to strengthen.

AI 正在改变开发者的工作方式:编写代码依然重要,但开发者还需要学会指挥 AI、评估其输出并作出可靠的技术决策。GitHub 建议重点强化三项能力:有效协调 AI Agent、不要盲信 AI 的首次回答,以及利用 AI 腾出的时间解决更高层级的问题。随着 AI 承担更多实现工作,技术判断、权衡取舍和识别正确问题的能力,将成为开发者和工程团队更关键的竞争力。
打开原文相关 5 · 机会 5
media75.6 KB media33.6 KB media84.8 KB media40.0 KB media60.5 KB media30.0 KB media127.1 KB media52.6 KB media77.9 KB media37.0 KB media70.2 KB media34.5 KB media84.0 KB media42.8 KB media238.5 KB media34.0 KB media6.3 KB media33.0 KB media48.5 KB media23.6 KB

中文

AI 正在改变开发者的工作方式,以及他们运用技能的方式。编写代码依然至关重要,但开发者越来越需要知道如何指挥 AI、评估其输出、沟通权衡取舍,并作出可靠的技术决策。

好消息是:你今天就可以开始准备。以下是值得重点关注的方向:

建议 #1:学习指挥 AI,而不只是使用 AI

AI 正在改变“执行”意味着什么。越来越多时候,出色的执行意味着清晰定义问题、提供恰当的上下文、评估 AI 生成的代码,以及决定哪些内容已经可以发布。随着 AI Agent 承担更多实现工作,这些技能会变得更加有价值。

例如,假设你需要新增一个身份验证流程。

传统工作流可能如下:

任务:新增身份验证  

→ 创建分支  
→ 编写代码  
→ 运行测试  
→ 创建拉取请求

随着 AI 工具能力不断增强,并更深入地融入日常工作流,同样的技能可以帮助你协调多个 AI Agent。你的工作流可能更接近这样:

工作区:新增身份验证  

Agent 1 ✓ 身份验证功能已准备好供审查 
Agent 2 ✓ 文档草稿已准备好  
Agent 3 ✓ 测试套件已准备好

注意其中发生的变化。你仍然要对最终结果负责,但自己亲手实现每一个部分的时间会更少。相反,你负责定义工作、审查输出,并作出将所有部分整合起来的技术决策。

要点: 学会指挥 AI Agent。

开始你的首次 Agent 会话 >

建议 #2:不要相信 AI 的第一个答案

AI 可以在数秒内生成令人印象深刻的解决方案,但第一个答案并不总是最佳答案。你在编写整洁、可维护代码方面的经验,可以帮助你评估 AI 的输出。

让第二个 AI 模型审查第一个模型的工作,然后用你自己的判断来评估这两份回答。

以下提示展示了实际操作中可能的样子:

“编写一条 SQL 查询,返回每位客户最近的一笔订单。”
↓
AI 模型 #1
✓ 生成查询语句
↓
AI 模型 #2(审查)
⚠ 未处理重复时间戳
⚠ 缺少索引建议
⚠ 在大型表上可能性能较差

不同 AI 模型具有不同的优势和盲点。因此,GitHub Copilot 内置的 Rubber Duck Agent 会在你继续之前,使用第二个模型审查计划、代码和测试。第二个视角往往能发现第一个模型遗漏的问题。

要点: 可以足够信任 AI 来使用它,但不要信任到跳过审查。

建议 #3:使用 AI 解决更大的问题

当 AI 节省了实现时间,开发者就可以将这些时间用于处理更广泛的问题:理解客户需求、评估权衡取舍、设计更好的系统,以及作出 AI 无法替代的技术决策。

例如:

Issue #4821 
标题:新增深色模式 

AI 

✓ 构建实现方案 
✓ 生成测试 
✓ 更新文档 

开发者检查清单 

☐ 验证客户问题 
☐ 审查架构权衡 
☐ 检查无障碍性 
☐ 定义成功指标 
☐ 批准解决方案

随着 AI 承担更多实现工作,区分优秀工程师与普通工程师的能力会变得更加重要:运用可靠判断、平衡权衡取舍,以及解决正确的问题。

要点: 让 AI 承担更多实现工作,从而让你投入更多时间培养判断力,帮助团队作出更好的决策。

核心结论

随着开发者工作流不断演进,学习如何有效地与 AI 协作,并强化自身的技术判断力,能够帮助你适应变化。

将这些理念付诸实践 >

作者

Gwen Davis 是 GitHub 的高级内容策略师,主要撰写有关开发者体验、AI 驱动工作流和科技行业职业成长的内容。

English / 原文

AI is changing how developers work and apply their skills. Writing code is still essential, but developers increasingly need to know how to direct AI, evaluate its output, communicate tradeoffs, and make sound technical decisions.

The good news? You can start preparing today. Here’s where to focus:

Tip #1: Learn to direct AI, not just use it.

AI is changing what execution looks like. Increasingly, great execution means defining the problem clearly, providing the right context, evaluating AI-generated code, and deciding what’s ready to ship. As AI agents take on more of the implementation, these skills become even more valuable.

For example, imagine you’re asked to add a new authentication flow.

A traditional workflow might look like this:

Task: Add authentication  

→ Create branch  
→ Write code  
→ Run tests  
→ Open pull request

As AI tools become more capable and more deeply integrated into day-to-day workflows, those same skills can help you coordinate multiple AI agents. Your workflow might look more like this:

Workspace: Add authentication  

Agent 1 ✓ Authentication ready for review 
Agent 2 ✓ Documentation draft ready  
Agent 3 ✓ Test suite ready

Notice what changed. You’re still responsible for the outcome, but you’re spending less time implementing every piece yourself. Instead, you’re defining the work, reviewing outputs, and making the technical decisions that bring everything together.

Takeaway: Learn to direct AI agents.

Start your first agent session >

Tip #2: Don’t trust AI’s first answer

AI can generate impressive solutions in seconds, but the first answer isn’t always the best. Your experience writing clean, maintainable code can help you evaluate AI’s output.

Ask a second AI model to critique the first model’s work, then use your own judgment to evaluate both responses.

Here’s a prompt that shows what that might look like in practice:

"Write a SQL query that returns each customer's most recent order." 
↓ 
AI Model #1 
✓ Generates the query 
↓ 
AI Model #2 (Critique) 
⚠ Doesn't handle duplicate timestamps 
⚠ Missing index recommendation 
⚠ May perform poorly on large tables

Different AI models have different strengths and blind spots. That’s why GitHub Copilot’s built-in Rubber Duck agent uses a second model to critique plans, code, and tests before you move forward. A second perspective often catches issues the first model misses.

Takeaway: Trust AI enough to use it but not enough to skip review.

Tip #3: Use AI to solve bigger problems

When AI saves implementation time, developers can use that time to tackle broader problems: understanding customer needs, evaluating tradeoffs, designing better systems, and making technical decisions that AI can’t make for them.

For example:

Issue #4821 
Title: Add dark mode 

AI 

✓ Build implementation 
✓ Generate tests 
✓ Update documentation 

Developer checklist 

☐ Validate customer problem 
☐ Review architectural tradeoffs 
☐ Check accessibility 
☐ Define success metrics 
☐ Approve solution 

As AI takes on more implementation work, the skills that distinguish great engineers become even more important: exercising sound judgment, balancing tradeoffs, and solving the right problems.

Takeaway: Let AI handle more of the implementation so you can spend more time building the judgment that helps teams make better decisions.

The bottom line

As developer workflows evolve, learning to work effectively with AI—and strengthening your own technical judgment—can help you adapt.

Put these ideas in practice >

Written by

Gwen Davis is a senior content strategist at GitHub, where she writes about developer experience, AI-powered workflows, and career growth in tech.