·AI
I Evaluated 40 AI Podcasts Across 7 Languages. Six Pipeline Fixes Later, Here's What Improved.
I built an eval framework to grade my AI podcast pipeline across 40 real episodes in 7 languages. The review step was making scripts worse (3.34 → 2.91). Citation URLs all looked fake (score: 1.28). Chinese was the weakest locale (2.88). Six fixes, one day, and a new model later — here are the before/after numbers and every change I made.