The Archive

Benchmark finds five System-1 decision models statistically match GPT-5.6 judge performance on eleven tasks at lower cost without reasoning.

Study compares selection bias across Jev-style System One models, Jev reproductions, and generative LLMs using multi-option shuffling tests to evaluate whether decision structure reduces bias.

JEV and Qwen Flash compared for clinical trial prescreening on 2,048 patient records under zero data retention constraints.

Span readout and selective adaptation techniques for natural language entailment reranking in JEV decision models.

PathJev-P applies decision-native architecture to histopathology, returning calibrated probabilities over expert-labeled candidate sets.

OpenAI is launching its decision model to the world. Can it compete with the original Jev?

Framework for continual learning from user corrections in interactive systems via typed feedback interfaces.

and from Baseten are now available for free on AI Gateway for one week. Free access is available through October 27. These decision models classify text, route requests, and score content against criteria you define.Mammoth-1Elephant-1 Mammoth-1 is the larger, 27B model, while Elephant-1 is a smaller, 9B option. Mammoth-1 is #1 on the Jev Decision Index and Elephant-1 is tied for #1 on the Artificial Analysis Decision Index. Both support a 16k-token context window and return choices, probabilities, and scores. Ask several questions about the same input in one request: select a support team wi...

main.content table { display:block; width:100%; max-width:100%; overflow-x:auto; } #evaluation-prompt pre { background:var(--bs-body-bg); color:var(--bs-body-color); padding:18px; border:1px solid var(--bs-border-color); border-radius:6px; } #evaluation-prompt pre code { color:inherit; white-space:pre-wrap; overflow-wrap:anywhere; } Decision models have exploded onto the scene recently, starting with TypeSafe’s Jev, followed by Perplexity’s Decider, Liquid’s d1, Cloudflare’s Clef, and OpenAI’s Decisions API1. These models promise fast, inexpensive classification. Decision models are an appeal...

The data comes from Vercel's AI gateway, a unified API service similar to OpenRouter.

Qwen-Audio-Jev adds specialized decision heads to Qwen-Audio-3.1 for low-latency selection/scoring tasks, reducing autoregressive overhead.

is now available on .Jev 1.14 from TypeSafe AIAI Gateway Jev is a for software. You pass it state and a set of questions, and it returns typed Choice, Score, and Boolean answers with probabilities instead of free-form text. It answers every question in one request, in parallel, for classification, routing, scoring, and automated verification.decision model Jev 1.14 accepts images as part of the state, and has an experimental long-context mode for documents, logs, or conversation histories that are too long for a standard request. Use as the model name.typesafe-ai/jev-1.14.0 Pass an image as a...

Jeva proposes structural requirements for System One decision-making models: null-awareness, permutation-invariance, option-scalability, and cacheability.

Startup claims $100M+ ARR and $7.5B valuation 3 weeks post-launch; lacks technical details or verification.

TypeSafe AI raised $870 million in a round led by a16Z.

Jev decision model tested as Q-function and policy provider in RL; single-pass generation without token-by-token decoding compared to foundation model priors.

Evaluation of Jev evidence verifier for financial LLM outputs reveals citation misattribution risks when numerically-identical cells enable paraphrased wrong-role claims.

LLM2Jev framework extracts calibrated categorical decisions from LLM next-token probabilities without fine-tuning, enabling direct software integration.

HydroJEV training-free classifier achieves one-second triage of SCADA alarms in water networks vs. LLM baselines.

Amazon Web Services' Strand Labs has released the latest Jevalike decision model, Strands Decider 2B.

Commentary on low-cost machine evaluation abundance prompted by TypeSafe AI's Jev model for probabilistic decisions.

OpenAI's computer use API shipped in one week; podcast interviews CUA and platform leads on DevDay announcements and capabilities.

OpenAI's "Decisions API" is a Jev clone that confirms the importance of fast, cheap intelligence.

Empirical comparison of Jev decision-oriented model vs. LLM reranking for structured recommendation tasks; tradeoff between quality and serving efficiency.

Ollama now supports decision models, based on TypeSafe's Jev API for fast, typed decisions. Decision models can now be run at no cost with low latency. Based on text, decision models answer yes-or-no questions, choices and scores about it, with a probability for every option.

Jev 1.13, a non-generative System One model, evaluated on medical QA and diagnostic reasoning against GPT-6 Sol across MetaMedQA, PubMedQA, DiagnosisArena-MCQ, NEJM Case Challenges.

Study reveals probabilistic incoherence in LLMs (Jev, English Laya) when decomposing classification decisions across hierarchical category levels.

Natural contextual additions can flip decisions in routing models (Jev) despite correct answers remaining valid.

Jev-Mobile reduces VLM inference cost in mobile GUI agents by decoupling low-frequency planning from high-frequency lightweight execution.

Compares nine LLMs and Jev on ContractNLI legal document inference, isolating decision consistency from answer accuracy.