Anthropic's Claude system prompts transformed into a git timeline for exploring prompt evolution via git log, diff, and blame.
Explores how naming AI chatbots creates distinct personalities, termed the 'Digital Ouija Effect', and its implications.
A critique of sharing AI chatbot screenshots, highlighting sycophancy, asymmetry of thought, and preference for human ideas over LLM outputs.
Explains good vs bad harness engineering for AI, emphasizing context over prescriptive instructions.
How an AI workflow evolved from manual prompts to automated skills, memory, and verification for more efficient code generation.
litprompt is a markdown preprocessor for LLM prompts that supports annotated comments and imports to manage complex prompts in git repos.
Explores how clear communication and context design improve AI and human team output, drawing parallels between prompt engineering and management.
Explains grounding in LLMs: connecting them to reliable data for accurate, context-aware responses using techniques like RAG and fine-tuning.
A guide to managing context in ChatGPT for better AI results, covering tools like custom instructions, memory, projects, and CustomGPTs.
Explores the challenges of getting consistent, reliable answers from AI models like ChatGPT due to prompt sensitivity and hidden variables.
Explains how token limits and context windows cause AI coding agents to fail, and offers techniques to keep them stable during long tasks.
Explores context engineering for AI coding agents, covering configuration features, reusable prompts, and tools like Claude Code to improve developer experience.
Introduces context engineering as a superior alternative to prompt engineering for AI coding assistants, enabling them to understand your codebase for consistent, high-quality results.
Prompt engineering is evolving from a niche skill to a core capability, similar to spreadsheet proficiency, as AI adoption grows across industries.
A developer shares key lessons from using AI agents full-time, focusing on workflow improvements, prompt strategies, and productivity gains in software development.
A guide to writing effective specifications for AI coding agents, covering principles like starting with a high-level vision and breaking down tasks.
A technical workflow using AI to transform hand-drawn mind maps into searchable, shareable digital visualizations in a consistent illuminated manuscript style.
Explores how AI prompts have evolved from simple text strings into critical, reusable system components with logic, and the challenges this creates.
Best practices and structural patterns for effectively prompting the Gemini 3 AI model, focusing on directness, logic, and clear instruction.
A deep dive into Google's Nano Banana (Gemini 2.5 Flash) AI image model, exploring its autoregressive architecture and superior prompt engineering capabilities.
