Wikipedia link race: choosing among thousands of options
The model chooses the next step from hundreds or thousands of links, demonstrating fast decisions with constrained outputs. The post includes a 4:04 video.
Jev Reranking Comparison: Evidence Coverage and MRR Gains
Analyzed 36 retrieval queries across 3 knowledge collections, comparing original ranking with TypeSafe AI's Jev on identical candidate sets. Evidence coverage@10 improved from 83.3% to 91.7%.
What does reranking buy you when the candidates stay the same? We reanalyzed 36 retrieval queries across 3 knowledge collections, comparing the original ranking with Jev from @typesafeai on identical candidate sets. • Evidence coverage@10: 83.3% → 91.7% • MRR@10: 0.647 →
· 1 likesOpen on X
More like this
Semantic Querying Use Case with Jev and TypeSafe AI
Nathan LeClaire shares a semantic querying use case for Jev and TypeSafe AI, noting people have only scratched the surface.
Building a live BS meter for the Trump vs Kamala debate with Jev
The author used Jev to run a live BS meter on every sentence of the Trump vs Kamala debate, with 5 yes/no questions per candidate, totaling 1,191 Jev calls, 1.18M tokens, 415 ms median latency, and $0.0497 total cost.
