Artificial intelligence news.
Straight from the original announcements.

Jev

Fiddler tests TypeSafe's Jev as a fast, cheap judge for coding agent risk
ResearchSeptember 30, 2026

Fiddler tests TypeSafe's Jev as a fast, cheap judge for coding agent risk

Fiddler AI tested TypeSafe AI's new Jev model as a judge of coding agent risk and found it returned ratings faster and at a lower estimated cost than two general-purpose…

OpenAI's Decisions API Targets Fast Agent Choices, but Details Remain Unpublished
BusinessSeptember 30, 2026

OpenAI's Decisions API Targets Fast Agent Choices, but Details Remain Unpublished

OpenAI's Decisions API, announced at DevDay 2026, restricts GPT-6 Luna to developer-defined questions with a finite list of answers, so agents can branch on a selection…

Jev model matches gpt-4o-mini judge on 897 of 1,000 turns, at lower cost
ModelsSeptember 30, 2026, 00:11

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
ResearchSeptember 28, 2026, 19:28

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
ModelsSeptember 28, 2026, 13:45

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
For developersSeptember 28, 2026

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
Products and toolsSeptember 25, 2026, 13:56

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
BusinessSeptember 25, 2026, 11:00

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…

Research
ResearchSeptember 25, 2026

Jev 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…

12