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
TypeSafe AI, founded by former OpenAI RLHF researcher Diogo Almeida, has emerged from two years of stealth development with $40 million in funding and its first product, a model called Jev. Rather than generating conversational text like ChatGPT, Jev is built to deliver fast, cheap yes/no or categorical decisions—in about a tenth of a second and for a fraction of a cent—aimed at software-to-software interactions rather than human chat.
techspot.com
· 2026-09-20
An independent developer has released Laya, an open-weight, non-autoregressive decision model that predicts structured outcomes in under 35 milliseconds using reinforcement learning with calibrated decisions (RLCD) and routing across more than 100 languages. The creator says the underlying approach dates back to a March 2025 arXiv paper and open Hugging Face weights, predating TypeSafe AI's closed, proprietary Jev model launched in September 2026 by AI figure Diogo Almeida's team.
laya.convaiinnovations.com
· 2026-09-19
Diogo Almeida, a former OpenAI researcher who helped invent RLHF and build ChatGPT, has released a new transformer-based model called Jev through his startup TypeSafe AI. Unlike large language models, Jev doesn't generate text—it produces calibrated probability outputs, making it faster, cheaper and immune to hallucination. Developers have shown strong demand, with the company briefly unable to keep up with API traffic.
techcrunch.com
· 2026-09-18
TypeSafe has open-sourced Jev Ultrafast, a browser automation agent that reads a page's elements as an indexed table and picks an operation-target pair in a single network round trip, calling a small language model only when text needs to be generated. In a demo, it booked a Zürich-to-London flight search on Google Flights from a single natural-language goal in 7.1 seconds, including page load waits. The code, along with a local inspector interface for watching element probabilities and executed actions, is available on GitHub.
github.com
· 2026-09-17
A new open-source tool called typesafe-computer-use lets a Mac execute plain-English goals by reading the screen state directly rather than sending screenshots to a large multimodal model. It uses a lightweight classifier from TypeSafe to pick the next action from a short list of options, only invoking a text-generation model when free-form input is actually required. The developers report costs near 1/50th of a cent per decision step, versus tens of cents per step for a comparable Claude Opus-based screenshot approach.
github.com
· 2026-09-16
GoKawiil