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.
Using Jev to search 6TB of old drives for $6
The author shares a first hands-on Jev use case: searching 6TB of old drives to find the most valuable files, costing $6 to complete a task postponed for years, with an open-source repo.
Riding the #Jev train, my first hands-on use case was searching through 6TB of old drives to find which files have the most value. This cost $6, finishing a task that I've put off for years due to the manual attention it would've required. Repo is open source 👇🏼
· 3 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.
