Building a Product Search Relevance Benchmark with WANDS
How I found, cleaned, and sampled the Wayfair WANDS dataset to build a validation benchmark for judgement-ai, my LLM based search relevance grading tool.
How I found, cleaned, and sampled the Wayfair WANDS dataset to build a validation benchmark for judgement-ai, my LLM based search relevance grading tool.
I built an LLM judgement tool to grade query result pairs
Run a locally fine-tuned coding AI with optional AMD GPU acceleration.
Learning Swift's concurrency model coming from Ruby on Rails - understanding async/await, task groups, and actors without the documentation jargon.
A comprehensive framework guiding product builders from initial hypothesis (A) to market success (Z) by prioritizing user psychology, minimizing friction, and adhering to strict quality principles.
How I prevented my AI app from maxing out my OpenRouter API key by building a production ready cost tracking gem
An analysis of recent job posting data to understand the trends shaping the software developer job market and strategies for early-career developers.
How I added an invitation solution to the built in rails 8 authentication solution so sign ups require an invitation code.
Learn how to efficiently compare commits in VSCode using GitLens—a must-know skill for debugging and version control.
Implementing React concepts learned so far, including state management, side effects, and using data from an external API.