Models & Labs
Typesafe AI Launches Jev Decision Model
Matt Wolfehigh confidence
Why it matters
- →Introduces a new paradigm of non-text AI outputs focused on speed and cost.
- →Drastically reduces inference costs compared to traditional LLMs.
- →Targets use cases where binary decisions or scores are sufficient, bypassing token-heavy text generation.
Typesafe AI has released Jev, an artificial intelligence model designed to bypass traditional text generation in favor of direct decision-making outputs. Unlike standard large language models that produce paragraphs or code snippets, Jev generates structured data such as choices, numerical scores, and true/false values. The company highlights significant efficiency gains, citing input costs starting at just 4 cents per million tokens, with output costs described as negligible. This architecture aims to provide a faster and more cost-effective alternative for applications requiring immediate logical conclusions rather than verbose explanations.
Read originalThe story around this
TopicJev AI ModelCooling
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1AI Engineers Use Loops Instead of Prompts
Cole Medin · June 18, 2026 · Background
- 2AI Tools Boost TypeScript's Dominance on GitHub
AI News · August 21, 2026 · Background
- 3Hugging Face Explores Boundary-Aware AI Safety
Hugging Face Blog · September 8, 2026 · Background
- 4Typesafe AI launches Jev for high-speed classification
Sam Witteveen · September 18, 2026 · Same story
- 5Jev: A Decision-Only AI Model for Agents
Cole Medin · September 21, 2026 · Same story
- 6Together AI: Fine-tune Jev-like classifier for $17
Together AI Blog · September 23, 2026 · Background
- 7Jev AI: Real-World Use Cases Beyond LLMs
The AI Daily Brief · September 26, 2026 · Background
What happened next
- 8Ollama adds Jev-style decision models
Ollama Blog · September 29, 2026 · Background
- 9Jev as a Smart Router for Agent Harnesses
Sam Witteveen · September 29, 2026 · Related
- 10OpenAI launches Decisions API for fast agent classification
TechCrunch AI · September 30, 2026 · Related
- 11Axiom raises $2B; TypeSafe AI gets $870M
Crunchbase News · October 9, 2026 · Background
- 12Hugging Face defines decision models for structured AI outputs
Hugging Face Blog · November 10, 2026 · Background
Follow this story
Open the full story →Typesafe AI Launches Jev Decision Model
2 developments
- Sep 28 · Matt Wolfe
Typesafe AI Launches Jev Decision Model (This article) - Oct 9 · TechCrunch AI
TypeSafe AI raises $870M for non-text model Jev↳ TypeSafe AI raised $870M from Andreessen Horowitz and Sequoia for Jev, with claims that a third of Fortune 500 companies are already using i
More in Models & Labs
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
llama.cpp Releases
Models & Labscoding
llama.cpp b12342 adds few-row MMQ for speculative decoding
Speculative decoding just got a significant speed boost on NVIDIA GPUs. This release introduces a specialized kernel for 'few-row' matrix multiplications, targeting the small batch sizes typical of verification passes in speculative decoding workflows. By optimizing these specific operations for quantized formats like Q8_0 and IQ4 variants, llama.cpp reduces latency where it matters most during token generation. The change is CUDA-only for now but leverages hardware capabilities from Ampere onwards, making local inference faster without requiring new model architectures or complex configuration changes.
llama.cpp Releases
© TechCrunch AIModels & Labsmodels
Google deploys Gemini 4 Hydrogen for faster Search
Google is quietly shifting its search infrastructure by replacing older fast models with Gemini 4 Hydrogen, a tier designed specifically for speed and cost-efficiency rather than raw reasoning power. This model completes tasks 2.5 times faster than its predecessor while beating the more powerful Argon on specific intelligence benchmarks, proving that specialized efficiency can outperform brute force in high-volume workflows. By integrating this into Search's fan-out technique, Google now breaks down complex queries into subqueries with greater precision and speed, delivering richer visual responses without the latency of heavier models. This marks a strategic pivot toward agentic execution layers within consumer search, making AI Mode feel snappier for everyday multi-part questions.
TechCrunch AI