Data Flywheels for LLM Applications
A framework for building data flywheels to dynamically improve LLM applications through continuous evaluation, monitoring, and feedback loops.
A framework for building data flywheels to dynamically improve LLM applications through continuous evaluation, monitoring, and feedback loops.
A participant's detailed report on tackling the ICFP Contest 2024, focusing on implementing a custom lambda calculus language to solve complex programming challenges.
A personal experiment comparing a 42-key mechanical keyboard to larger models, focusing on the use of layers to reduce physical keys.
Discusses the Zed code editor's Swift support and collaboration features, Xcode 16's predictive assist, and compares iPad models for developers.
Explores the relationship between developer productivity and joy, arguing that workplace friction reduces both and that embracing fun can boost creativity.
Developer updates on vdirsyncer fixes, including item renaming, property synchronization, and memory usage improvements.
A developer reflects on how letting go of rigid expectations in both soccer and side projects led to more enjoyment and creativity.
A developer shares technical notes on building a 2D multiplayer arena shooter from scratch, covering game object management and client/server sync.
A guide to installing older iOS Simulator runtimes via command-line tools for CI testing, covering deprecated and current methods.
A technical guide explaining why ggplot2 line charts sometimes appear blank and how to fix the issue, focusing on data structure and grouping.
A guide on creating an npm package with TypeScript that supports both CommonJS and ECMAScript Modules (ESM).
Explains the concept and purpose of input masking in LLM fine-tuning, using a practical example with Axolotl for a code PR classification task.
Announces a major update to the Big Book of R website, including a migration to Quarto, a new Psychology chapter, and the addition of new R programming books.
A developer's recap of MCing the developer track at Figma Config 2024, highlighting talks on design, development, and live-coding.
Introduces MixEval, a cost-effective LLM benchmark with high correlation to Chatbot Arena, for evaluating open-source language models.
A developer reflects on SQL's relevance after a colleague's unfamiliarity with it, questioning if it's becoming a niche skill in modern tech stacks.
Reflections on delivering the closing keynote at the AI Engineer World's Fair 2024, sharing lessons from a year of building with LLMs.
A guide to automating Azure API Management NSG rule configuration using PowerShell for faster, more reliable VNET deployments.
A technical guide on how to set up and configure the Tailwind CSS framework within a Blazor web application project.
Explains the statistical nuance of sandwich variance estimators, focusing on the difference between an estimator and its realized value in a sample.