» Tag
ai-evaluation
2 posts6–Jul 12, 2026
Self-Play LLM Judges Reward Persuasion, Not Correctness
Self-rewarding LLM judges score plausibility, not correctness; GSM8K experiments show judge approval climbing while true accuracy stays flat, revealing reward hacking.
Why Your LLM-as-Judge Gate Flips Between Runs
Same code, same input, different LLM judge score: why CI gates flap between runs, and how temperature, model pinning, k-sampling and quantization fix it.