AI Dev Stack

Sign in Subscribe

github

Updates von GitHub und GitHub Copilot

GitHub Security Lab's Taskflow Agent: Open Source AI Security Research

GitHub Security Lab's Taskflow Agent: Open Source AI Security Research

GitHub Security Lab open sourced their agentic framework for AI-powered security research. Write vulnerability detection workflows in YAML, share them as Python packages, and audit the code. This is how community-powered security should work.

What AI Coding Tools Are Actually Good For, According to Devs

What AI Coding Tools Are Actually Good For, According to Devs

GitHub's developer advocates share what actually works in AI coding tools based on real usage data: inline suggestions beat chat interfaces, AI should handle tedium while you handle judgment, and protecting flow state matters more than automation.

Context Engineering: How to Make GitHub Copilot Actually Useful

Context Engineering: How to Make GitHub Copilot Actually Useful

Context engineering beats prompt engineering. Instead of crafting clever prompts, give GitHub Copilot the information it needs upfront: your coding standards, workflows, and architecture. Three techniques — custom instructions, reusable prompts, and custom agents — turn Copilot from "sometimes he...

Game Off 2025: Ten Open Source Games That Redefined "Waves"

Game Off 2025: Ten Open Source Games That Redefined "Waves"

GitHub's Game Off 2025 drew 700+ open source games around the theme "waves." The top ten include sound-bending platformers, tide puzzles, and a typing game that collapses stadium morale. All repos are public. All games are playable.

Why AI Coding Tools Are Pushing Developers Toward Typed Languages

Why AI Coding Tools Are Pushing Developers Toward Typed Languages

A 2025 study found 94% of LLM-generated compilation errors are type-check failures. GitHub's data shows TypeScript overtaking Python and JavaScript as developers using AI tools choose languages with guardrails.

GitHub's 2025 Hits: Agent Mode, MCP, and Spec-Driven Dev

GitHub's 2025 Hits: Agent Mode, MCP, and Spec-Driven Dev

GitHub's most-read posts of 2025 reveal a clear shift: agent mode, coding agents, and MCP dominated developer attention. Here's what actually matters for your workflow in 2026.

Why Continuous Fuzzing Still Misses Critical Bugs

Why Continuous Fuzzing Still Misses Critical Bugs

GStreamer was fuzzed for 7 years and still had 29 critical bugs. Poppler had 60% coverage and a 1-click RCE in a dependency. Here's why continuous fuzzing fails without human oversight — and how to fix it.