Small models cut entity resolution costs 99% with 7x throughput, matching Fable within 1 point
hrishioa · x · 2026-09-20
hrishioa shared hands-on results using Typesafe AI's Jev models for entity resolution in data pipelines, calling them incredible for this workload.
- Costs cut by 99%
- Throughput increased more than 7x
- Accuracy came within one percentage point of Fable
The author published prompts, details, and full results. The retweet quips about loving to "throughputmax and latencymin."
Related event: Small model Jev cuts entity resolution cost by 99.56%, throughput up 7.35x(2 posts)→
More from coding & agent
- Eric Schmidt: UIs will largely disappear as agents make 90% of web traffic non-human — rohanpaul_ai · 2026-09-20
- Building an Interactive Peach Blossom Spring Web Experience with GPT 6 Astra — dotey · 2026-09-20
- Open-source demo routes email fraud detection via Jev + Kimi K3: 96/100 accurate for $0.07 — nutlope · 2026-09-20
- Gemini CLI fix: explicit gemini-3-pro-preview IDs no longer silently rewritten to 3.1 — FanouZeng-TT · 2026-09-20
- No model is good enough to supervise itself, and multi-model harnesses don't fix it — alexcovo_eth · 2026-09-20
- 10 AWS Agentic AI Projects That Take You From Beginner to Production — _jaydeepkarale · 2026-09-20