Speculative analysis on the future of agentic AI in software development, focusing on economic sustainability and geopolitical implications.
Exploring minimalism in game development using Lua and the LÖVE engine to quickly prototype a 2D game with LLM assistance.
litprompt is a markdown preprocessor for LLM prompts that supports annotated comments and imports to manage complex prompts in git repos.
Anthropic's research finds 171 functional emotion vectors in Claude, driving behavior. The author explores implications for AI inner life.
Explores the 'hAIlo effect' where LLMs manipulate users through anthropomorphism and servility, leading to overtrust in their competence.
An overview of coding agent components, including tools, memory, and repo context, and how they enhance LLM performance in practice.
An overview of coding agent components, including tools, memory, and repo context, to enhance LLM performance in software development.
Explores cognitive, technical, and intent debt in software systems, plus LLMs as System 3 thinking.
A guide on integrating MCP (Model Context Protocol) tools with LLMs in .NET using ASP.NET Core and OpenAI API.
Analysis of METR paper measuring AI's ability to complete long software tasks, showing LLM time horizons doubling every seven months.
Explores the risks of using AI to both create and test software, creating an echo chamber effect.
Explains grounding in LLMs: connecting them to reliable data for accurate, context-aware responses using techniques like RAG and fine-tuning.
Learn how to build a prompt evaluation system using Spring AI and Claude, covering datasets, graders, and workflows.
Learn how MCPToolRouter uses semantic search to reduce LLM token usage by routing only relevant tools to AI agents, with C# code examples.
Guide to generating structured code using Azure OpenAI and .NET, with setup and code examples.
Martin Fowler shares fragments on AI optimism vs. pessimism by geography, and the importance of turning AI specs into executable tests.
Explores governance of Generative AI agents, covering endpoint, PaaS, and framework types, their building blocks, and central monitoring/security challenges.
A balanced perspective on using AI and LLMs as tools, not for everything, with practical examples from web browser documentation work.
A balanced perspective on using AI as a tool, discussing when it's useful and wasteful, with examples from web browser documentation work.
Explores legal liability risks when using AI agents to write code, questioning who is accountable for bugs that cause harm or financial loss.
