Models & Labs
Jev: A Decision-Only AI Model for Agents
Cole Medinhigh confidence
Why it matters
- →Replaces expensive LLM calls for simple routing decisions with ultra-low-cost inference.
- →Offers sub-200ms latency suitable for real-time agent loops and game logic.
- →Introduces a new model class focused purely on probabilistic decision gates.
TypeSafe has launched Jev, an AI model designed exclusively for decision-making rather than text generation. The system accepts state inputs and typed questions, returning decisions with probabilities in approximately 200 milliseconds at a fraction of a cent per call. Early use cases include automating game logic, triaging pull requests, and routing requests between different large language models. This approach positions Jev as a specialized component for agentic coding workflows where speed and cost efficiency are critical.
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
- 1Benchmarking Open Models for Agentic Use
Hugging Face Blog · June 18, 2026 · Related
- 2Agentic AI Loops: The Next Big Step?
TechCrunch AI · June 22, 2026 · Related
- 3Google Releases Playbook on Agentic Engineering
Cole Medin · June 25, 2026 · Related
- 4Memora Enhances AI Memory for Long-Horizon Tasks
Microsoft Research · June 29, 2026 · Related
- 5Claude Sonnet 5: Enhanced Agentic AI Model
Anthropic · June 30, 2026 · Related
- 6Scaling AI Agents with Redis Iris
Cole Medin · July 9, 2026 · Related
- 7ThunderAgent Boosts Agentic Inference Efficiency
Together AI Blog · July 29, 2026 · Related
- 8Grok Bot Simplifies AI Agent Adoption
The AI Daily Brief · August 13, 2026 · Related
What happened next
- 9Typesafe AI Launches Jev Decision Model
Matt Wolfe · September 28, 2026 · Same story
- 10Jev as a Smart Router for Agent Harnesses
Sam Witteveen · September 29, 2026 · Same story
- 11OpenAI launches Decisions API for fast agent classification
TechCrunch AI · September 30, 2026 · Same story
- 12Liquid AI releases efficient on-device agent model
Hugging Face Blog · October 13, 2026 · Related
- 13Together AI automates inference optimization with agents
Together AI Blog · November 4, 2026 · Related
Follow this story
Open the full story →TypeSafe Launches Jev Judgment Model
7 developments
- Sep 17 · The AI Daily Brief
TypeSafe Launches Jev Judgment Model - Sep 18 · Sam Witteveen
Typesafe AI launches Jev for high-speed classification↳ Jev prioritizes System 1 reasoning for ultra-fast classification, targeting latency bottlenecks in agent workflows rather than chain-of-thou - Sep 18 · TechCrunch AI
TypeSafe AI launches Jev, a non-LLM model for automation - Sep 21 · Cole Medin
Jev: A Decision-Only AI Model for Agents (This article)↳ Jev abandons text generation to become a pure decision engine with sub-200ms latency and negligible costs. - Sep 21 · Fireship
Ex-OpenAI researcher launches Jev System 1 model↳ Ex-OpenAI researcher Diogo Almeida launches Jev System 1, claiming it is 200x faster and 400x cheaper than standard LLMs by stripping out te - Sep 22 · Duncan Rogoff
Jev AI Classifier: Speed vs. Hype↳ Jev excels at rigid schema-based routing but fails on open-ended generation or complex reasoning. - Sep 23 · Together AI Blog
Together AI: Fine-tune Jev-like classifier for $17↳ Together AI fine-tunes Qwen3.5 4B into a Jev-style classifier for $17 in 25 minutes.
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
llama.cpp Releases
Models & Labsother
llama.cpp b12182 release with CUDA 13 and ROCm 10
This release quietly cements llama.cpp as the universal inference runtime by adding default builds for CUDA 13.5 and ROCm 10.0 across Linux and Windows. The inclusion of ROCm 10 means AMD GPU users no longer need custom compilation to access modern acceleration, effectively closing the gap with NVIDIA's ecosystem support. While KleidiAI on Apple Silicon is disabled in this build, the broader platform coverage ensures that local inference remains accessible on virtually any hardware configuration without manual setup.
llama.cpp Releases