Guidea16z.com
Investing in TypeSafe AI
Andreessen Horowitz explains why it led the round. It calls the Jev launch the biggest narrative violation it has seen this year, and says Jev reached 1 trillion tokens generated in 3 days after launch.
Updated Oct 12, 2026
Resources for building with Jev
Docs and reading for a first Jev call: TypeSafe’s quickstart and cookbooks, the LangChain harness guide, the awesome-jev lists and the launch coverage.
- 838builds
- 176guides
- 21use cases
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Guidehuggingface.co
Decision models on the Hugging Face Hub
Hugging Face gave decision models their own tag, an icon on model pages and a filter on the Models page. GGUF decision models are tagged automatically from their llama.cpp metadata.
Guidenishtahir.com
Build your own decision model
Nish Tahir builds one from Qwen3-1.7B: constrain the output to a fixed set of options, read the probabilities in one pass, then fix the overconfidence with temperature scaling. It comes with a repository of scripts to build a dataset, evaluate, fine-tune and calibrate.
Guidejahanzaib.ai
Microsoft Decision-1: price, latency and porting from Jev
Jahanzaib’s guide to moving a Jev integration to Microsoft Decision-1. The endpoint path ends in /v1/systemone, the request has the same state and typed questions, and the price is the same $0.042 per million input tokens with free output.
Jev docs and cookbooks
What to read before you build: TypeSafe’s own quickstart, docs and cookbooks, the LangChain harness guide, the awesome-jev lists other builders keep, and the launch coverage.
176 guides