LLM
5 posts
AI Tools I Actually Use
A practical rundown of the AI products I use daily for software development and work - no hype, just what actually works for me.
Deep Research Systems: Architectural Differences That Matter
A technical analysis of how modern AI research systems actually work, comparing ReAct, test-time compute scaling, and hybrid reasoning architectures.
Native Structured Outputs: When to Skip the Framework
OpenAI and Anthropic now offer built-in structured output support. Here's when to use native APIs versus validation frameworks.
Comparing Python Libraries for Structured LLM Extraction
A practical comparison of instructor, outlines, and pydantic-ai for getting structured data from LLMs based on production experience.
I Tested LLM Prompt Caching With Anthropic and OpenAI
Experiments testing prompt caching with actual API calls, measuring cache hits, token counts, and costs across Anthropic Claude and OpenAI GPT.