Jev
Jev model matches gpt-4o-mini judge on 897 of 1,000 turns, at lower cost
A model that returns probabilities for yes/no questions instead of writing text was 3.5× cheaper and 3.8× faster than a gpt-4o-mini judge on 1,000 real production turns…
Arize test: Jev's probabilities flag its own errors and hard cases for LLM judges
Arize AI says Jev, a model that returns a probability for each label instead of generating text, can show where an evaluation is likely wrong or hard from a single call.…
LangChain Pairs TypeSafe's Jev Decision Model With LangGraph for 'Prod, Not God' Agents
LangChain has published a guide to building production agents with Jev, a decision model released by TypeSafe AI, and its own LangGraph framework. The idea is to let…
Mastra adds classifiers for fast, predictable decisions with evaluation models
Mastra has introduced classifiers, a feature that lets developers use evaluation models to answer structured questions and make fast, predictable decisions in their…
Picsart Plugin Arrives in Grok Bot, Bringing Image, Video and Audio Tools to Chat
Picsart is now available as a plugin in Grok Bot, xAI's assistant and bot builder, so users can request images, video, audio and edits in plain English and get finished…
Pydantic AI Gateway adds Jev, TypeSafe's classification model
Pydantic has made Jev, TypeSafe's classification model, available through Pydantic AI Gateway. Applications can call it with the same gateway key they use for language…
ResearchJev misses subtle errors in harder LLM judge test, MLflow finds
TypeSafe's Jev judge model agreed with human labels on 64 of 72 answers in a harder MLflow test, while GPT-OSS-120B matched all 72. Jev was far faster and cheaper, and…