Jev

2026-10-30

MODELS · 1 SOURCE · InfoQ AI, ML & Data Engineering

InfoQ podcast: AI, ML and Data Engineering Trends Report 2026

InfoQ's AI, ML and Data Engineering editorial team published a 2026 trends report and released a podcast episode where editors and guest Chip Huyen discuss key trends: a shift toward smaller language models and reasoning models, wider deployment of AI agents (from personal to organizational), interest in System One models such as TypeSafe AI's Jev for cheaper/faster inference, growing focus on AI evaluations, and advances in Physical AI. The panel also offered near-term predictions including more US robotics innovation, cost and energy constraints on infrastructure, broader use of specialized/mixed agents, and continued delineation of tasks best suited for AI versus humans.

4.0

2026-10-23

MODELS · 1 SOURCE · arXiv cs.AI

Decision language model Jev rivals many LLM judges for clinical AI evaluation while being far cheaper and faster (arXiv preprint)

An arXiv preprint compares Jev, a decision language model that outputs structured judgments, against frontier and open-weight LLM judges across four clinical-evaluation use cases. On 118 pediatric answers Jev's agreement with physician ordinal ratings (Gwet's AC2 0.50; expected 0.53) matched or exceeded seven of 12 LLM judges (including Claude Opus 5.5 at 0.49 and GPT-6 at 0.38); Jev matched or exceeded several judges on HealthBench and MedHELM tasks and matched GPT-5.4 on 91% of HealthBench Professional criteria, while frontier judges cost 73–294× more and took 7–57× longer.

7.0

2026-10-20

MODELS · 1 SOURCE · The Decoder

Cloudflare previews Clairic, a document-extraction model for Workers AI

Cloudflare released Clairic in preview on Workers AI, an AI model that extracts named fields from documents in a single pass (returning values, formats and confidence scores) and which the company says is faster and cheaper than using LLMs; open weights are slated to follow. Cloudflare notes Clairic can perform simple calculations and forecasts but currently isn't reliable for longer calculation chains and is intended to run in chains alongside other System One models like Jev, Clef and GLM-5.3.

7.0

2026-10-16

MODELS · 1 SOURCE · TechCrunch AI

Typesafe’s Jev becomes fastest-adopted model on Vercel gateway

Vercel data shows that Jev, a lightweight decision model from Typesafe AI released in limited form on Sept. 15, was used by 35% of paid teams within two weeks—nearly double the reach of the next model, Sonnet 5.5. Vercel, which used Jev to replace GPT-6 Luna for some harmful-command classification, cautions its gateway data may undercount providers that run their own APIs; the report also notes open-source models now account for over 70% of tokens on Vercel and about 25% of spend while frontier-lab spending has grown tenfold.

6.0

2026-10-16

MODELS · 1 SOURCE · InfoQ AI, ML & Data Engineering

AWS open-sources Strands Decider 2B and launches Strands Box sandbox for agent execution

AWS released Strands Decider 2B, a 2-billion-parameter decision-focused model (based on Qwen3.5-2B with a pointer head and rank-16 LoRA) and published the model weights, training data, and scripts. It also announced Strands Box (developer preview), a kernel-enforced sandbox using the Dogwood policy language to control agent execution (shell, Python, tools, filesystem, network); AWS reports ~115 ms median decision latency on an RTX 3090 and 72.3% accuracy on JevBench for a v19 checkpoint.

7.0

2026-10-16

RESEARCH · 1 SOURCE · arXiv cs.AI

RealtimeBench benchmark and TORSI method evaluate LLM agents under a live clock

arXiv:2610.20665v1 introduces RealtimeBench, a 180‑task benchmark across six game types that evaluates language‑model agents while environments continue running during inference, and proposes TORSI (Two‑Timescale Offline Recursive Self‑Improvement). The paper reports that GPT‑6.1‑sol outperforms a faster model (Jev) when games are paused but falls behind when games run continuously; applying TORSI—where a slow teacher produces reusable instructions for a fast student and validation gates updates—raises Jev’s average test score from 13.51 to 24.19 and transfers improvements to three other models without retuning.

7.0

2026-10-10

MODELS · 1 SOURCE · The Decoder

Microsoft releases Decision-1 decision model based on Qwen3.5-9B

Microsoft announced Decision-1, a decision-oriented model built on Qwen3.5-9B that Microsoft says handles classifications, evaluations and routing decisions. Microsoft claims Decision-1 is the most accurate model in its tests across 36 benchmarks (nearly 150,000 questions) and 2.5× faster than the runner-up H2O-Lightning-4B; the company offers Decision-1 via Microsoft Foundry and OpenRouter with input tokens priced at $0.042 per million and output tokens free, and notes Cloudflare's Clef models were not included in its comparison.

7.0

2026-10-09

STARTUPS · 1 SOURCE · TechCrunch AI

TypeSafe AI raises $870M at $7.5B valuation for non-text model Jev weeks after launch

TypeSafe AI said it raised $870 million at a $7.5 billion valuation for Jev, a transformer-based model that outputs probabilities rather than text, in a round led by Andreessen Horowitz with Sequoia and DCVC participating. Jev launched on Sept. 15 and the company says a third of Fortune 500 companies are already using it and that it runs faster and uses fewer tokens than LLMs, claims the startup has made about the product.

8.0

2026-10-05

RESEARCH · 1 SOURCE · arXiv cs.AI

Labels override definitions in Jev-style typed decision models (arXiv:2610.02586v1)

The paper analyzes Jev-style typed decision interfaces across four open-weight models (Qwen2.5 backbones), eleven classification tasks and a synthetic suite called PolicyBench, and shows that models often follow short option labels rather than their written definitions (an "option-label bias"). Deleting or renaming labels can change accuracy substantially without altering model weights; one codebase ('von') avoided the effect by formatting options as definitions only. The authors provide a two-call test to detect which behavior applies and evaluate four mitigation strategies.

7.0

2026-10-02

MODELS · 1 SOURCE · The Decoder

Cloudflare launches Clef and Clef-flash decision models (Qwen-based)

Cloudflare released two decision models, Clef (based on Qwen3.8-27B) and the smaller Clef-flash (Qwen3.5-9B), which output probability-weighted choices for predefined answers so downstream agents can act automatically. The company says both support text and images, report median latencies of ~209 ms (Clef) and ~39 ms (Clef-flash), are compatible with TypeSafe AI's Jev API, available on Hugging Face under Apache-2.0, and will be accompanied by a reinforcement-learning service for customer fine-tuning.

8.0

2026-10-01

MODELS · 1 SOURCE · TechCrunch AI

AWS open-sources Strands Decider 2B, a Jev-style decision model

Amazon Web Services’ Strands Labs released Strands Decider 2B, an open-source, compact decision model inspired by TypeSafe’s Jev that selects between pre-defined options and reports calibrated confidence scores; the model is built on a Qen3.5-2B torso, is small enough to run locally, and was developed by AWS engineer Marc Brooker. The release, which briefly topped Jevbench for its size, arrived the same week OpenAI announced a similar offering and reflects growing interest in lightweight decision models for agentic workflows.

7.0

2026-09-30

MODELS · 1 SOURCE · TechCrunch AI

OpenAI previews Decisions API — a Jev-like fast decision model for Luna

At its Dev Day, OpenAI’s CEO Sam Altman revealed the Decisions API, a limited-preview product that lets the Luna model output probabilities over a predefined set of choices (e.g., classifications or agent behaviors) at high speed and low cost. Media and industry observers note the API resembles TypeSafe AI’s recently released Jev; proponents say such decision-focused models could cheaply monitor or gate agentic actions, though exact capabilities and calibration remain unclear.

7.0

2026-09-28

RESEARCH · 1 SOURCE · arXiv cs.AI

LAVOIR: single-pass decision encoder that predicts value-of-information to decide when to ask

LAVOIR (Laya with Value-Of-Information Routing) augments Laya-style single-pass decision encoders to output both a decision distribution and, for each candidate missing information slot, an expected value-of-information (VOI) so the system can decide whether to ask a question. The method creates VOI training targets without human labels, uses a Gini-impurity cap to bound predicted VOI, matches a Bayes ceiling on seen schemas, achieves AUC 0.799 vs. a greedy oracle 0.797, improves accuracy by up to 14.1 points with ≤0.5 questions per conversation, and reduces asking on SGD from 93% to 8.6%; median answer latency is 31 ms on GH200.

6.0

2026-09-18

MODELS · 2 SOURCES · The Decoder · TechCrunch AI

TypeSafe AI unveils Jev, a model that scores predefined options instead of generating text

Startup TypeSafe AI, co-founded by ex-OpenAI researcher Diogo Almeida, introduced Jev, a model designed to return narrow labels and probabilities (judgments) for developer-defined questions rather than free-form text. TypeSafe says Jev responds in 70–500 ms and is very cheap (listed at $0.042 per million input tokens), but its published benchmarks are limited, comparisons use the company's own workflows, and the model's "no hallucination" claim only applies to output structure, not correctness within allowed choices.

7.0