Skip to content

@nutlope classified 100 emails (50 legit, 50 fraudulent) with Jev in 1.42 seconds, then sent the 31 predictions under 95% confidence to Kimi K3. The combined pipeline was 96/100 correct in 16 seconds for about $0.07, of which about $0.003 was Jev.

Benchmarks

Hassan @nutlope

EN

  • 52.8k views
  • 843 likes
  • 739 bookmarks
  • 47 reposts
Poster from Hassan (@nutlope)

About this case

Hassan (@nutlope) published this on 2026-09-17. @nutlope classified 100 emails (50 legit, 50 fraudulent) with Jev in 1.42 seconds, then sent the 31 predictions under 95% confidence to Kimi K3. The combined pipeline was 96/100 correct in 16 seconds for about $0.07, of which about $0.003 was Jev. Jev + 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! How Jev or TypeSafe is used, in the post's own words: “Jev + Kimi K3 for fraud detection!” The post does not name a separate audience. It is for people reading what @nutlope shows here (it includes media).

Original posthttps://x.com/nutlope/status/2100614659690713543

Related cases