The post notes that conversational AI is great for drafting emails but too slow for real-time fraud detection; modified Jev-like models bypass text generation and evaluate business parameters in a single pass for instant predictions.
Conversational AI is great for drafting emails, but natural language generation is too slow for real-time fraud detection. A new breed of modified Jev-like models bypasses text generation entirely, evaluating business parameters in a single pass for instant predictions. However,
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.