Classifier scores 100 YouTuber videos for sales intent in 12s at ~$0.02
eptwts · x · 2026-09-18
A developer used the Jev classifier to analyze a YouTuber's last 100 videos for sales intent, scoring each in about 12 seconds total for roughly $0.02. Accuracy hasn't been deeply validated, but a quick glance suggests it's a promising classifier — useful for influencer vetting and sponsorship analysis.
Related event: Jev Model Scores 100 Videos for Sales Intent in 12 Seconds for 2 Cents(2 posts)→
More from Models
- Leaked GPT-6 Astra tops FrontierSWE at 65.5%, compresses 600MB audio to 20KB — soumitrashukla9 · 2026-09-18
- Muse Code 'crazy cheap and quite good': early take on Meta's coding model — AIandDesign · 2026-09-18
- Community unmasks stealth model Union Alpha as Unbiased's Pareto 26.9 in one day — gaganghotra_ · 2026-09-18
- Emad Mostaque hails an 'Opus 4.5-level' model that runs on 8GB RAM — ccerrato147 · 2026-09-18
- Astra computer use formats Google Docs autonomously, leaving users impressed — var_epsilon · 2026-09-18
- jev may have unseated Cohere as the best reranker on speed, cost, and performance — multiply_matrix · 2026-09-18