Sequence Is Not Structure: Getting Lost in Long LLM Conversations
Long LLM conversations preserve sequence, not structure. I want a way to see where ideas branch, drift, and remain unfinished.
Reflections on code, craft, and the future of software
Long LLM conversations preserve sequence, not structure. I want a way to see where ideas branch, drift, and remain unfinished.
A small fallback service and rclone made it possible to move Active Storage files to a new S3 bucket without downtime.
A walk through the design choices for showing rich UI in an LLM chat app instead of plain text bubbles. Tools, schemas, and a tiny gem for generative UI on top of RubyLLM.
Share Extensions can no longer open your app directly. A comparison of four approaches to handle authentication in iOS 18.
How to build reliable word pronunciation for language learning apps using LLM-based TTS instead of dictionary APIs. Covers handling heteronyms with IPA substitution and building a practical pronunciation pipeline.
Exploring two underused Rails routing features — direct and resolve — through 37signals' newly open-sourced Fizzy codebase. Learn how to create custom URL helpers and teach Rails to generate polymorphic URLs for models without their own routes.