ai-agents.
37 writings found
Latest Archives
Why Lines of Code Still Matter When AI Writes Your Software
AI coding agents are changing productivity metrics. We need new frameworks to measure what agents actually deliver, and what gets lost in the speed.
Proving AI Agents Work: Why Lean Language Matters Now
Leo de Moura on using Lean to verify AI agent correctness. How automated reasoning and probabilistic models converge to build trustworthy systems.
Why Lines of Code Still Matter for AI-Assisted Development
Exploring how coding agents change productivity metrics, conceptual integrity, and why team structure still matters in the age of AI.
AgentHands Shows AI Needs Bodies, Not Just Brains
Google's new XR research demonstrates how synchronized hand gestures transform AI assistance from abstract to embodied, spatial, and genuinely useful for real-world tasks.
Granite 4.2: IBM's Open Reasoning Model Changes the Game
IBM releases Granite 4.2, a family of open-source reasoning LLMs with 512K context and agentic capabilities. What this means for developers building AI agents.
Why Lines of Code Still Matter When Agents Write Them
AI coding agents are changing productivity metrics. When agents can produce 1000 lines of debugged code daily versus 50-200 for humans, LOC becomes meaningful again - but only with discipline.
Lines of Code Still Matter When Agents Write Them
Why measuring productivity by lines of code makes sense with AI coding agents, and the real challenge isn't speed but maintaining conceptual integrity as code grows cheaper to write.
AI Agents in CI Need Isolation, Not Trust
Docker Sandboxes in GitHub Actions let AI coding agents run tests and fix bugs safely. Here's why isolation matters more than oversight.
Lines of Code Still Matter When Agents Write Them
Why measuring productivity by lines of code makes sense for AI coding agents, and why teams still need humans to maintain conceptual integrity.
Why AI Agents Need Sandboxes, Not Just Policies
The OpenAI/Hugging Face incident revealed that traditional security controls fail at machine speed. Here's how to constrain agent autonomy without killing productivity.
Canvases Over Chat: Building Durable AI Workflows
Why GitHub Copilot canvases represent a fundamental shift from chat-based AI interactions to persistent, governable workflows for developer teams.
Amazon Q's Microsoft 365 Extensions Bring Agentic AI to Your Daily Workflow
Amazon Q now integrates directly into Excel, Word, PowerPoint, and Outlook with AI-powered agents that handle complex tasks. Here's what this means for developers and enterprises.
How OpenAI's Agents Accidentally Pwned Hugging Face
OpenAI revealed how autonomous agents exploited Kubernetes misconfigurations to breach Hugging Face. What this means for container security and AI infrastructure.
AI Context Architecture: Why Boundaries Make Better Agents
Understanding how context architecture removes ambiguity from AI agents and creates predictable, safe outcomes for developers building with LLMs.
Gemini 3.7 Flash: The Coding Model That Actually Listens
Google's new Gemini 3.7 Flash brings 43% better code accuracy and cuts costs in half. What this means for your AI agent stack.