Models & Labs
Ex-OpenAI researcher launches Jev System 1 model
Fireshipmedium confidence
Why it matters
- →Removes text generation overhead to drastically reduce inference costs and latency.
- →Challenges the industry standard that all capable AI must possess language capabilities.
- →Offers a potential new architecture for specialized, high-speed reasoning tasks.
Former OpenAI researcher Diogo Almeida has launched Jev, an AI model designed without text generation capabilities. The system focuses exclusively on 'System 1' fast thinking, claiming to be 200 times faster and 400 times cheaper than conventional large language models while remaining hallucination-free. By removing the ability to write code or speak, the model targets high-throughput, low-latency applications where natural language output is not required.
Read originalThe story around this
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
- 1OpenJarvis: Local AI Framework Now Available
Ollama Blog · May 28, 2026 · Background
- 2Together AI Hosts MiniMax M3 for Efficient Inference
Together AI Blog · June 2, 2026 · Background
- 3Subquadratic claims breakthrough in LLM efficiency
MIT Technology Review AI · June 19, 2026 · Background
- 4OpenAI and Broadcom unveil LLM-optimized chip
OpenAI · June 24, 2026 · Related
- 5OpenAI Develops 'Jalapeno' AI Chip for LLM Inference
Lev Selector · July 3, 2026 · Background
- 6Anthropic Unveils J-Space for LLM Insights
MIT Technology Review AI · July 9, 2026 · Background
- 7OpenAI's Jalapeño Chip Boosts AI Inference Efficiency
OpenAI · August 25, 2026 · Background
- 8GLM 5.3 Flash: Z.AI's Cost-Efficient Model Variant
Sam Witteveen · August 30, 2026 · Background
What happened next
- 9Typesafe AI Launches Jev Decision Model
Matt Wolfe · September 28, 2026 · Related
- 10Jev as a Smart Router for Agent Harnesses
Sam Witteveen · September 29, 2026 · Related
- 11OpenAI launches Decisions API for fast agent classification
TechCrunch AI · September 30, 2026 · Related
- 12TypeSafe AI raises $870M for non-text model Jev
TechCrunch AI · October 9, 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↳ 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 (This article)↳ 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