A user reports that TypeSafe's Jev is faster than GPT-4o-mini on 250 real expense categorization tasks, and on 3,600 expenses cites higher accuracy, ~9x speed and ~7x cost advantage, noting they are testing it.
Mismo trabajo. 250 gastos reales para categorizar. 🐢 GPT-4o-mini (lo que usamos hoy): 13 min 14 s ⚡ Jev de @TypeSafe: 1 min 24 s Sobre 3.600 gastos: ✅ +4 puntos de precisión (58,5% vs 54,5%) ⚡ 9x más rápido (1,6 s vs 14,4 s por gasto) 💸 7x más barato Lo estamos probando
James Long uses Jev to tackle the most annoying problem in personal finance tools: generating good payee descriptions from raw bank data. It got about 95% of the way there on the first try, with many ways to improve the prompting.
A developer uses Jev to decide buy or sell and executes real trades on Kuru's on-chain order book via Monad every 300ms block. Link
Erik Spock Gafni suggests that those who make a lot of profit from Jev trading donate some of their profits to charity.