微软要一刀裁掉大半个Meta，Copilot沦为重灾区
微软开始掏钱请员工主动考虑离职。 约6万人有资格接受这份邀请，超过公司全球员工的四分之一。 这次不用等到临近退休，也不要求绩效不好。符合条件的员工可以拿着补偿，在年底离开公司。颇有点迫不及待想多甩掉一些人的感觉。 连微软寄予厚望的Copilot团队，也在覆盖范围内。遥想今年春天，其他部门暂停招聘的时候，Copilot团队还在招人。...
微软推出 Copilot 混合推理架构：云端本地模型可自动切换 本月底上线
微软宣布 GitHub Copilot 将于本月底前支持本地 AI 模型推理，开发者可在云端模型与设备端模型之间自动或手动切换。目前 GitHub Copilot 依赖云端托管模型，由协调器根据性能、成本与准确性路由请求。扩展后平台将支持自动编排或强制使用设备端模型两种模式，用户可在相关工具中设置偏好，还可指定本地模型的提供程序、模型或端点。微软同步推出...
微软放弃封禁 Microslop
微软 CEO 纳德拉（Satya Nadella）关于 AI 的著名评论促使网民为微软起了 Microslop 的绰号，绰号的流行和随处可见促使微软今年早些时候在官方 Copilot Discord 服务器将其封禁，用户输入 Microslop 后会收到警告称根据服务器规定其输入包含了不合适的短语。但用户很快找到了应对之策，创造了无数 Microslop...
微软花费 12 万美元 token 将 Copilot 运行时移植到 Rust 语言
微软利用使用 GPT-5.6 Sol 和 Claude Opus 4.8 的 AI 智能体、历时 14.5 周，花费 12 万美元 token 将 Copilot 运行时从 TypeScript 语言移植到 Rust 语言。该项目采用逐个更新运行时模块的方式执行，共进行了 135 次发布，平均每天提交约 1.3 个 Pull Request，最终将 43...
AI-Generated GitHub Copilot “Autofix” Allowed Compromise of Snowflake's Jira
Article URL: https://www.wiz.io/blog/red-agent-snowflake-copilot-cicd-bug Comments URL: https://news.ycombinator.com/item?id=49331423 Points: 194 # Comments: 89
Local LLM on a 16GB Mac Mini: Replacing GitHub Copilot with Ollama + Qwen
I kept paying a monthly subscription for a cloud coding assistant while a 16GB M4 Mac mini sat on my desk idling most of the day. So I ran the obvious experiment: can a 16GB Mac mini run a coding assistant entirely offline — no code leaving the machine, no subscription — and is it actually usable for real work? Short answer: yes, with one hard constraint (RAM) and one soft one (context length). This article is the written version of the video above, with every command, config file, and benchmark number so you can reproduce it. Table of contents Why bother running locally The hardware constraint nobody mentions Step 1: Install Ollama Step 2: Pick a model that fits in 16GB Step 3: Run and verify Step 4: Wire it into VS Code Step 5: Tune Ollama for a 16GB box Benchmarks What it does well,...
GitHub Copilot AI Credits vs Claude Code: The Real Math on What Your AI Coding Costs Now
Three months ago, almost every AI coding tool had the same deal: pay a flat monthly fee, use it until you hit a wall. That era is over. On June 1, 2026, GitHub flipped Copilot from counting requests to metering tokens, and the reaction was immediate and ugly. The GitHub community discussion announcing the change has 24 thumbs up and 958 thumbs down. Some developers reported their effective costs jumping 10x to 50x overnight because of which model they had selected. Meanwhile Claude Code never left the flat-rate model. It just quietly throttles you instead: a five-hour rolling usage window, a weekly cap, and since March, reduced limits during weekday peak hours. So which billing model actually costs you less? I spent an evening with GitHub's published rate sheets, Anthropic's plan limits,...
GitHub Copilot app for Beginners: Write your first prompt
Opening a new AI tool can feel a little like staring at a blank page. You know you want help with something, but figuring out exactly what to ask can be its own task. The good news is that you don’t need to write the perfect prompt to get started. A prompt is simply a description of what you want to accomplish. Start with what you know, give Copilot some context, and refine the request as you go. Let’s walk through what it looks like to start your first task in the GitHub Copilot app. Start with the right context Before you can ask Copilot to make a change, it needs something to work on. Agent sessions can be connected to a GitHub repository or a folder on your local machine, giving Copilot access to the code and files it needs for the task. From the GitHub Copilot app home...
GitHub Copilot app for Beginners: Managing your work
This is the third post in our GitHub Copilot app for Beginners series. If you’re just joining us, check out, GitHub Copilot app for beginners: Getting started, where we introduced the app and how it helps you work across multiple agent sessions. Our second post goes deeper on working within a session. Here, we’ll look at how to keep all of the requests and work being done on a project organized in one place. If you’ve been following along in this series, you know that real development is rarely a straight line. You fix a bug here, review a pull request there, and chase down a new idea somewhere in between. As you continue to assign tasks to Copilot and create new pull requests, you’ll quickly find yourself with several proverbial balls in the air. Being able to...
Write your first prompt with the GitHub Copilot app
Opening a new AI tool can feel a little like staring at a blank page. You know you want help with something, but figuring out exactly what to ask can be its own task. The good news is that you don’t need to write the perfect prompt to get started. A prompt is simply a description of what you want to accomplish. Start with what you know, give Copilot some context, and refine the request as you go. Let’s walk through what it looks like to start your first task in the GitHub Copilot app. Start with the right context Before you can ask Copilot to make a change, it needs something to work on. Agent sessions can be connected to a GitHub repository or a folder on your local machine, giving Copilot access to the code and files it needs for the task. From the GitHub Copilot app home...
Using the GitHub Copilot SDK for Java
Java developers no longer have to rely on Java framework-specific approaches to drive AI from their enterprise apps. While it is true that Langchain4j empowered developers by disintermediating specific AI vendors, you still had a dependency on Langchain4j. And with Spring AI, well, of course you had a dependency on design choices made by Spring, if not on Spring itself. Now, GitHub Copilot SDK for Java is the first truly framework agnostic way to drive AI from Java. And with its BYOK support, GitHub Copilot SDK for Java is also AI vendor neutral. Even though it’s called GitHub Copilot SDK, you can use it with any direct model provider, such as OpenAI, Azure, Anthropic, or OpenAI-compatible endpoints, by passing a / with your own + (or bearer token). No Copilot subscription required....
When Is GitHub Copilot Actually Worth the Subscription? A Break-Even Analysis
The honest answer: a paid Copilot tier pays for itself the moment it saves you more time per month than the subscription costs at your effective hourly rate — which, for most working developers, is a very low bar. The harder question is whether you specifically clear it, because Copilot's value depends heavily on the language you write, how much boilerplate your work involves, and whether the free tier already covers you. This post gives you a formula to run the math for your own situation instead of trusting a vendor's "10x productivity" slide. I've run Copilot daily across TypeScript, Python, and Go work for long enough to have a clear sense of where it earns its keep and where it quietly wastes your time. Let's make the decision numeric. What do you actually get at each tier? GitHub...