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.
Qwen+Jev Layered SQL Security Architecture
The article analyzes an AI data analyst setup: Qwen generates SQL, Jev reviews it, and code decides what can run. Key rule: anything that can be code-checked should be code-checked.
Qwen пишет SQL, Jev его проверяет, а код решает, что вообще можно запускать. Разобрали ИИ-аналитика данных, где генерация, ревью и безопасность разнесены по разным слоям. Правило, которое стоит забрать себе: всё, что проверяется кодом, проверяйте кодом. https://uproger.com/ii-analitik-qwen-jev-sql/…
· 0 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.
