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.
OneStar: Analyzing App Reviews with Jev
Jared introduces OneStar, powered by TypeSafe's Jev model, which makes it cheap to ask questions across thousands of app reviews, revealing what users love, why they leave, and what they ask for. Launching on Product Hunt tomorrow.
Jev from @typesafeai made it cheap enough to ask the same questions about thousands of app reviews instead of sampling them. That's what OneStar does. Pick any app or game and it shows what people love, why they leave and what they ask for. Product Hunt tomorrow. 60 second demo
· 4 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.
