At OpenAI's Dev Day, CEO Sam Altman introduced a new 'Decisions API' that lets developers give the company's Luna model a predefined set of options to choose from, such as image categories or agent behaviors, returning fast, low-cost outputs. The tool appears similar to Jev, a classifier model released earlier this month by TypeSafe AI for software automation tasks. OpenAI's API is currently in limited preview, and TypeSafe did not respond to requests for comment on the similarities.
techcrunch.com
· 2026-09-30
TypeSafe AI has released Jev, a model designed to convert natural-language input and application state directly into typed decisions, returning choices, scores and probabilities as JSON. The company says Jev uses a new architecture, a parallel sampler, and a training method called Reinforcement Learning for Calibrated Decisions to generate probabilities without token-by-token generation. TypeSafe reports significant speed and cost improvements over general-purpose LLMs for decision-making workflows.
columnar.tech
· 2026-09-29
Andrew Boyd, founder of Standard Agents Inc., says his Jev decision model beat Pokémon Red's Elite Four and Champion, reaching the Hall of Fame on September 23, 2026, less than a week after the run began. Jev isn't a chatbot or LLM; it picks from lists of weighted options rather than reading the screen, while Anthropic's Claude Opus 5 monitored the game log and adjusted those options to help it when stuck. A harness changelog logged 474 fixes, including repeated failures like walking into a shut door 53 times and looping a ladder 124 times.
tomshardware.com
· 2026-09-27
A technical post describes a method for turning an off-the-shelf large language model, GLM-5.3-Flash running on Privatemode, into a decision-making model that outputs a typed choice with confidence scores in a single forward pass, rather than generating a full JSON response. Benchmarked against public datasets, the setup reportedly matches TypeSafe's specialized Jev model in decision accuracy and speed, while also supporting typed decisions on images, which Jev cannot do.
privatemode.ai
· 2026-09-26
Ollaya is a new local server for running open-source 'decision models' like Laya, gliclass and NLI, designed to answer structured questions in a single forward pass rather than generating text token by token. It implements the same /v1/systemone and /v1/models endpoints as TypeSafe's hosted API, so the official TypeSafe Python SDK can point at a local Ollaya server without code changes.
ollaya.dev
· 2026-09-25
A technical blog post examines TypeSafe's new Jev system, a 'System One Model' that converts unstructured input into typed decisions with attached probability scores instead of generating text. The author argues Jev is genuinely useful because it works without requiring training data, unlike a fine-tuned BERT model, but disputes TypeSafe's claim that its RLCD training method produces probabilities that are truly calibrated across any dataset.
alexmolas.com
· 2026-09-23
A GitHub project called jevper reimplements the documented 'System One' wire format used by the Jev interface, letting developers run typed questions (choice, score, noul) against any OpenAI-compatible model instead of the hosted TypeSafe API. It works with self-hosted llama.cpp servers or other duck-typed clients, requiring no dependency on typesafe-sdk or openai at runtime, and is installable via pip as a Python 3.10+ package.
github.com
· 2026-09-23
TypeSafe's Jev, a rapidly adopted AI classification model, has become the fastest-growing model in Vercel's AI Gateway history. A commentator argues OpenAI could quickly replicate Jev's core approach and bundle it directly into its own models and agents, since OpenAI's LLMs already function as implicit classifiers that could be retrained for this purpose.
arcturus-labs.com
· 2026-09-22
A Show HN post introduces JevBench, a benchmark that measures typed decision models by cost per 1,000 decisions rather than per token, using actual token counts from 534 v1.2 test decisions. The methodology prices systems with public tariffs at their listed per-token rates, while unlisted open-weight models are priced using OpenRouter or DeepInfra hosting rates for the same or comparable weights, explicitly avoiding raw GPU rental costs. Reported figures include Jev 1.13.0 at $0.0399 per 1,000 decisions, SemIf at roughly $0.022, and Winnow-12B Q8 at roughly $0.037.
benchmarkheaven.com
· 2026-09-22
TypeSafe AI has released Jev, its first 'System One' model designed not for conversation but for evaluating statements and making structured decisions for use in software systems. Built by former OpenAI researcher Diogo Almeida, the model claims to be up to 194x faster and 445x cheaper than frontier LLMs like GPT-6 Astra by processing parallel yes/no style queries with confidence scores instead of generating open-ended text.
tomshardware.com
· 2026-09-21
A new joke npm package called jev-leftpad reimplements string left-padding by calling an AI model (Jev, via TypeSafe's SDK) to choose how many spaces to add, rather than using JavaScript's built-in padStart() method. It requires an API key, Node.js 20+, and only supports padding up to 10 spaces since the AI is given choices labeled space_0 through space_10. The author explicitly warns against using it in production or for anything important.
github.com
· 2026-09-21
A developer has released Kev, a family of small decision-making models (0.8B, 4B, and 9B parameters) built on Qwen3.5, inspired by the architecture behind Jev. The models handle yes/no, multiple-choice, and rating questions within a single request and are compatible with TypeSafe's System One API, meaning developers can run Kev locally instead of relying on that hosted service. Full training code, evaluation data, and a web playground are included, and the models run on both CUDA and Apple Silicon hardware.
github.com
· 2026-09-21