Latest

LLMs got good enough that the hard problems shifted. I stopped writing about prompt engineering and started building autonomous coding agents. Here's what I learned moving from Claude Code to Pi, and why controlling an agent is harder than using one.

How adding observation masking to our existing LLM summarization reduced token costs, improved response latency, and eased rate limit pressure. Adapted from JetBrains research.

Learn how to secure user-uploaded images in S3 using CloudFront signed URLs, ensuring only authenticated owners can access their private assets.

I wanted to understand how multi-hop RAG works and see if DSPy lives up to the hype. Built a demo with the MuSiQue dataset to explore iterative retrieval with synthesis-in-the-loop. Here's what I learned about adaptive reasoning and why it makes a real difference.

Explore techniques to reduce token usage in LLM contexts by using compact data formats, summarization, and intelligent retrieval.