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.
Classifying a half-hour interview with JEV for emotional and controversial topics
Using JEV to classify T24's half-hour interview with Daron Acemoglu in just 3.7 seconds, identifying where emotional topics, controversial subjects, and anecdotes or humor appeared.
I classified the interview that T24 conducted with Daron Acemoglu using JEV. It took a total of 3.7 seconds. It revealed where emotional topics and where controversial subjects were discussed in the half-hour interview. It identified where there were anecdotes or funny
· 385 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.
