AIJev and Kimi K3 reportedly classify 96 of 100 emails correctly in fraud-detection demo
A user says Jev classified the emails in 1.42 seconds before they routed 31 low-confidence cases to Kimi K3. They report that the full run took 16 seconds and cost about $0.07 in inference.
TLDR
A user reports testing Jev on 100 emails: 50 legitimate and 50 fraudulent. Jev classified them in 1.42 seconds, and the user sent the 31 predictions below 95% confidence to Kimi K3. They say the combined pipeline got 96 of 100 correct, taking 16 seconds overall and costing about $0.07 in inference. Their approach pairs a specialized model for the initial classification with a larger language model for uncertain cases.
Combined views
56.4K
2 Sources, first seen 2d ago
Jev and Kimi K3 reportedly classify 96 of 100 emails correctly in fraud-detection demo
A user says Jev classified the emails in 1.42 seconds before they routed 31 low-confidence cases to Kimi K3. They report that the full run took 16 seconds and cost about $0.07 in inference.
