developer-tools.
33 writings found
Page 2
Permission Hungry Agents and the Return to First Principles
ThoughtWorks Radar 34 reveals AI's paradox: tools that generate complexity at speed while forcing us back to security basics and software fundamentals.
GitHub Copilot's Limits Crisis: When AI Agents Outgrow Their Infrastructure
GitHub just paused new Copilot signups and tightened usage limits. The reason? Agentic workflows are consuming resources faster than their pricing model can handle.
Building an Emoji List Generator Live: What GitHub's Rubber Duck Thursday Taught Me About AI-Powered Development
A live coding session reveals how GitHub Copilot CLI and multi-model AI workflows are changing how we build small tools. Here's what actually happened.
GitHub Copilot CLI Is Bringing Agentic AI to Your Terminal
The command line just got a lot more intelligent. GitHub's new Copilot CLI lets AI agents write code, fix bugs, and handle tasks autonomously from your terminal.
GitHub Copilot CLI: When Your Terminal Becomes Sentient (Sort Of)
GitHub's agentic AI moves into the command line. I spent time with Copilot CLI to see if coding from the terminal finally makes sense again.
LLMs Don't Actually Push You Toward Boring Technology
Coding agents work surprisingly well with new, undocumented tools. The 'training data bias' concern might be overstated in 2026.
Why Coding Agents Might Not Lock Us Into Boring Technology After All
Modern LLMs can learn new tools on the fly through documentation and examples. The feared training data bias might be less of an issue than we thought.
AI Skills Aren't the Gap. Access Is.
How Andela's AI training program reveals what really blocks developers in the Global South from participating in the AI era.
AI Is Quietly Deciding Which Languages Developers Choose Next
TypeScript just topped GitHub's language charts. The real story isn't the milestone, it's why AI compatibility is silently reshaping every tech decision you make.
Just-in-Time Tests: How Meta Is Rethinking Software Testing for the Agentic Era
Meta's JiTTests use LLMs to auto-generate bespoke tests per code change, killing false positives and test maintenance overhead in agentic dev workflows.
Building a Live Documentation Ecosystem for AI Coding Agents
Showboat's new remote streaming feature and companion tools create a real-time feedback loop for AI-assisted development workflows.
Building a Real-Time Documentation Ecosystem for AI Coding Agents
How Showboat's streaming updates, browser automation, and charting tools are changing the way we monitor and interact with AI coding agents in real time
Building Tools So AI Agents Can Actually Show Their Work
Two new CLI tools tackle a critical gap in AI-assisted development: proving that agent-generated code actually works without spending hours on manual QA.
Showboat and Rodney: Making AI Agents Prove Their Work
New CLI tools that force coding agents to demonstrate what they built, not just claim the tests pass. Because passing tests don't mean working software.
Continuous AI: Why GitHub is Betting on Agents That Reason, Not Just Execute
GitHub Next introduces Continuous AI, a new pattern for automating judgment-heavy engineering work that CI was never designed to handle.