GoKawiil
Tech News
A Show HN submission titled 'Jev Plays Pokémon Red' presents a fictional in-game dialogue from Pokémon Red as a vehicle to promote Frigade, an AI assistant that learns a product and guides users step-by-step inside an app. The post frames Professor Oak's guidance to the player as a metaphor for what Frigade offers to software users.
A technical write-up describes RLCD (Reinforcement Learning from Calibrated Decisions) as an evolution of reward modeling, moving from scalar reward scores to pairwise preference models like PPRM, and finally to a schema-conditioned, multiway probability distribution. It explains that Jev implements this RLCD objective by adding typed outputs and parallel inference, effectively turning the reward model itself into the primary decision-making system rather than a hidden scoring layer behind a generator.
Parcha has published AgentRun, a workflow language that lets developers define repeatable steps around existing AI agents, using a component called Jev for narrow decisions and invoking the agent itself only when deeper investigation is needed. The project is available via npm as a beta package, includes a demo ticket-routing workflow that runs without an API key, and ships with documentation, examples, and a Pi editor extension.
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.
A team has built safe-upgrade, a dependency-upgrade agent that separates three concerns: Jev converts release notes and repository evidence into typed, probabilistic decisions; LangGraph runs those decisions through a durable workflow; and Tenuo issues each resulting action a task-scoped warrant limiting its authority. The project uses dependency upgrades as a test case because passing installs and CI checks can still hide broken APIs or behavior changes that existing tests don't catch.
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.
A technical blog post demonstrates how the buzzy AI concept known as 'Jev' can be replicated using an open-source Qwen3-0.6B model and roughly 25 lines of Python code. The example loads the model, prompts it to classify an email as legitimate, spam, or phishing, and extracts probability scores directly from the model's output logits rather than relying on an external API or specialized training pipeline.
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.
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.
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.
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.
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.