Jev beats Gemini 2.5 Flash Lite on classifier eval quality and speed
Malte Ubl ran TypeSafe AI's Jev against an existing classifier eval, where it saturated the eval on quality and was 6x faster than Gemini 2.5 Flash Lite.
Jev in Lightdash data agents: 78% time reduction
After integrating Jev into Lightdash's data agents, a side-by-side comparison showed a 78% reduction in time and only 7% of the token usage. Full write-up coming soon and already rolling out to users.
We added jev into @lightdash_devs 's data agents and did a side-by-side comparison and the results were pretty epic. 78% reduction in time and only used 7% of tokens compared to without jev in the loop! Full write-up coming soon, and rolling out to users already :D
· 1 likesOpen on X
More like this
Fast row classification in DuckDB with Jev
The author released a DuckDB extension that uses TypeSafe AI's Jev to quickly classify rows in CSV/Parquet files or DuckDB tables, taking about 10 seconds for 1k rows—faster than an LLM and more ergonomic than a classifier.
Classifying 1,018 AI Papers with Jev for $0.08
The author summarized each paper with DeepSeek V4 Flash, then sent the title, summary, and 24 candidate topics to Jev for classification, processing 1,018 AI papers at $0.08 total cost and 256ms median end-to-end latency per paper.
