A weekly update on SkillsBar v1.7.0 release, Vale linting fixes, and AI eval exploration for documentation.
Explains AI evals: automated checks for non-deterministic AI outputs using LLMs to score against expectations, not exact matches.
A blog post summarizing key concepts from an AI Evals course, focusing on mental models like the 'Three Gulfs' for improving LLM applications.
A practical guide sharing lessons learned from a year of building real-world applications with Large Language Models (LLMs).
