An AI Odyssey, Part 4: Astounding Coding Agents
A developer shares personal experiences with AI coding agents, noting significant improvements in capability and efficiency, while discussing limitations and best practices.
A developer shares personal experiences with AI coding agents, noting significant improvements in capability and efficiency, while discussing limitations and best practices.
Analysis of AI coding agent criticism, arguing that non-users' abstract critiques lack practical experience.
Guide to building a benchmarking framework for AI coding agents using Claude's Agent SDK, focusing on security tasks.
A developer's reflection on resisting AI-driven multitasking and the benefits of focusing on one task at a time for well-being and productivity.
Explores why AI coding agents don't accelerate software delivery, arguing that code generation is no longer the primary bottleneck.
Introducing mcp-wire, a CLI tool that simplifies configuring MCP servers across multiple AI coding agents like Claude Code and OpenCode.
A critical analysis of why LLMs like Claude Code struggle with complex coding tasks, arguing the real issue is not intelligence but poor software engineering practices.
Kiro CLI now supports the Agent Client Protocol (ACP), enabling its AI agent to work within specialized IDEs like DataGrip for database tasks.
Introduces the Agent Client Protocol (ACP), an open standard for unifying communication between AI coding agents and code editors.
Explains the core concepts of AI coding agents (rules, commands, skills, etc.) and provides a unified mental model for understanding them.
A developer uses a single AI coding agent to build a basic web browser from scratch in Rust over three days, challenging assumptions about AI-assisted development.
A developer uses a single AI coding agent to build a functional web browser from scratch in Rust over three days, challenging assumptions about AI-assisted development.
Explores how managing multiple AI coding agents parallels tech leadership, shifting focus from code generation to orchestration and review.
Obie Fernandez reflects on AI coding agents shifting developer focus from writing code to decision-making and intent.
A developer argues that AI coding agents are not like junior developers but rather 'amnesiac spies' with vast knowledge but no memory or growth.