yuvhaim-gif/LLM_InSight

This is my personal home rig for serious LLM experimentation. I built it to test models head-to-head, create custom evaluation rubrics, automatically improve prompts based on the previous run’s results, and generate high-quality synthetic training data. Everything runs locally first (Ollama by default), with optional cloud support. logged locally.

2 best points · 2 comments · 4 Hacker News posts · 5 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: My "home rig" for iterative attribute-weighted LLM benchmarking (2 points, 1 comments, by yuvalhaim, 2026-05-04)
• Brand Voice Local Tunning Tool Demo (2 points, 0 comments, by yuvalhaim, 2026-06-15)
• LLM-Insights, local demo for people comments and ideas (1 points, 0 comments, by yuvalhaim, 2026-05-25)
• LLM_InSights (1 points, 1 comments, by yuvalhaim, 2026-06-03)