Dera News

Microsoft Copilot & AI

Microsoft Copilot across Office, GitHub, Azure, and Windows. Enterprise rollouts, licensing, integration patterns, and what works in real Japanese workplaces.

12 articles
Last 30 days
(14 total matching)
Google article thumbnail
Google and 3 others
Google

Meet GitHub Spec-Kit: An Open Source Toolkit for Spec-Driven Development with AI Coding Agents

If you have spent time using AI coding agents — GitHub Copilot, Claude Code, Gemini CLI — you have probably run into this situation: you describe what you want, the agent generates a block of code that looks correct, compiles, and then subtly misses the actual intent. This “vibe-coding” approach can work for quick prototypes The post Meet GitHub Spec-Kit: An Open Source Toolkit for Spec-Driven Development with AI Coding Agents appeared first on MarkTechPost.

Notable
Anthropic article thumbnail
Anthropic and 1 others
Anthropic

One command turns any open-source repo into an AI agent backdoor. OpenClaw proved no supply-chain scanner has a detection category for it

Just two months ago, researchers at the Data Intelligence Lab at the University of Hong Kong introduced CLI-Anything, a new state-of-the-art tool that analyzes any repo’s source code and generates a structured command line interface (CLI) that AI coding agents can operate with a single command. Claude Code, Codex, OpenClaw, Cursor, and GitHub Copilot CLI are all supported, and since its launch in March, CLI‑Anything has climbed to more than 30,000 GitHub stars. But the same mechanism that makes ...

Notable
Microsoft article thumbnail
Microsoft logo
Microsoft

Changes to GitHub Copilot Individual plans

GitHub is rolling out changes to its Copilot individual plans, focusing on improving reliability and transparency. These updates include enhanced status page details and a refreshed Transparency Center, giving users clearer insights into the platform's health and policy changes.

Microsoft article thumbnail
Microsoft logo
Microsoft

GitHub Copilot CLI for Beginners: Interactive v. non-interactive mode

GitHub has released a guide explaining the two main modes of Copilot CLI: interactive and non-interactive. This tool aims to integrate AI directly into the command line, promising to significantly enhance developer productivity. The article showcases practical applications, like generating emoji lists, and discusses how AI is reshaping software development, alongside the growing importance of understanding AI security.

Microsoft article thumbnail
Microsoft logo
Microsoft

GitHub Copilot is moving to usage-based billing

GitHub Copilot, the popular AI coding assistant, is switching to a usage-based billing model on June 1, 2025. This means companies will pay based on their consumption of GitHub AI credits instead of a flat fee per user. For SMBs, this change could make predicting development costs a bit trickier, requiring a closer look at how their teams use Copilot.

Microsoft article thumbnail
Microsoft logo
Microsoft

Building an emoji list generator with the GitHub Copilot CLI

GitHub has published an introductory guide for the command-line interface (CLI) version of its AI tool, GitHub Copilot. This guide offers a step-by-step tutorial designed to help developers quickly adopt and utilize Copilot CLI, which promises to enhance productivity by assisting with complex commands and script generation directly within the command line.

Microsoft article thumbnail
Microsoft logo
Microsoft

Microsoft launches ‘vibe working’ in Word, Excel, and PowerPoint

Microsoft Copilot in Office apps is leveling up with 'Agent Mode,' a significant evolution from its previous 'vibe working' capabilities. This new mode lets the AI directly manipulate documents, spreadsheets, and presentations in Word, Excel, and PowerPoint. For SMBs, this means a potential leap in automating routine tasks and boosting overall operational efficiency across the board.

Anthropic article thumbnail
OpenAI and 2 others
Anthropic

Claude Code, Copilot and Codex all got hacked. Every attacker went for the credential, not the model.

On March 30, BeyondTrust proved that a crafted GitHub branch name could steal Codex’s OAuth token in cleartext. OpenAI classified it Critical P1. Two days later, Anthropic’s Claude Code source code spilled onto the public npm registry, and within hours, Adversa found Claude Code silently ignored its own deny rules once a command exceeded 50 subcommands. These were not isolated bugs. They were the latest in a nine-month run: six research teams disclosed exploits against Codex, Claude Code, Copilo...