• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI

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.

2 Sources, 22d ago, first seen 22d ago

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

—

2 Sources, first seen 22d ago

— likes— comments— saves— reposts

Combined views

—

2 Sources, first seen 22d ago

— likes— comments— saves— reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

2 Sources

Hassan@nutlopeJev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on @togethercompute - $0.003 (1/3 of a cent) from Jev on @typesafeai. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.22d
Vipul Ved Prakash@vipulvedRT @nutlope: Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi…20d
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Hassan@nutlopeJev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on @togethercompute - $0.003 (1/3 of a cent) from Jev on @typesafeai. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.22d
    Vipul Ved Prakash@vipulvedRT @nutlope: Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi…20d
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet