Explores how Domain-Specific Languages (DSLs) guide LLMs to generate reliable, intent-aligned code, using Tickloom as an example.
Analysis of Cursor's AI coding usage data, revealing power users generate 10x more code and input tokens dominate costs.
Tips to improve AI-generated code quality using repeatable skills and structured prompts.
Using Z3/Python to solve a chess puzzle: place all pieces on a 6x5 board with no attacks.
A physicist turned AI developer explains creating Matrix Designer to enforce architecture and design before AI writes code, solving the problem of fragmented AI-generated software.
Recap of presenting at AWS New York Summit 2026 on agentic AI and spec-driven development for modernizing SDLC.
A developer compares AI code assistants OpenCode and Cursor, finding Cursor verbose and token-inefficient for bug fixes.
A software engineer reflects on the changing meaning of 'help' in tech, where coding is replaced by documentation and AI agents.
Microsoft announces MAI-Thinking-1 and MAI-Code-1-Flash LLMs, with low active parameters and claims of performance, but training data issues remain.
Wolverine and Marten improve F# support with pre-generated code and Roslyn optimizations for better deployment.
Explores how AI changes the definition of a 10x engineer, shifting focus from writing more code to higher-impact decisions and judgment.
A developer reflects on using AI-assisted programming tools like GitHub Copilot to create a Rust-based R package, sharing insights and experiences.
Explores the end of traditional coding, shifting from writing syntax to expressing intent and leading AI agents in software development.
A practical guide on using Agentic AI in software development, sharing a workflow for building projects with AI as a supportive tool.
A developer shares personal experiences with AI coding agents, noting significant improvements in capability and efficiency, while discussing limitations and best practices.
Customizing Wolverine code generation to create pure functions for HTTP endpoints, using automatic ReportId generation.
A reflection on AI's impact on content creation, drawing parallels to Tom Petty's 'The Last DJ' and questioning the role of human originality.
Proposes treating AI coding assistant instructions as versioned, shared infrastructure to encode team standards and ensure consistent code quality.
Explores the risks of using AI to both create and test software, creating an echo chamber effect.
Learn how to redact sensitive data in jOOQ 3.21+ logs using a code generation configuration to enhance security.
