Jev: TypeSafe's 70-500ms System One AI primitive costs $0.042 per million input tokens
daniel_mac8 · x · 2026-09-23
Dan McAteer breaks down Jev, a new ultra-fast, ultra-cheap "System One" AI primitive from Diogo Almeida (ex-OpenAI, co-author on the InstructGPT paper) and his team at TypeSafe.
What it is
- Response times of 70–500ms; $0.042 per million input tokens, output free.
- Unlike LLMs, you don't chat with it: you hand it a decision and it returns a probability distribution over options, predicting which is most likely correct.
How to build with it
- Inputs are the "state" (an email, document, or app state to evaluate) and a question about that state, defined via three types such as Choice over provided options.
- Jev shines inside programs making bounded judgments: you supply context and outcomes while code and LLMs handle surrounding work — the engineer's challenge is deciding which judgments to delegate.
- The post draws on TypeSafe docs and community experiments to explain how it works, how builders combine it with LLMs, and a test for whether your app can use it.
Related event: Ex-OpenAI researcher launches Jev, a non-text "System One" decision model(12 posts)→
More from coding & agent
- The decade of agents: simulate real customers to test your agent before launch — EXM7777 · 2026-11-11
- FluentCRM MCP Server lets you manage marketing automation from Cursor or Claude — modelcontextprotocol · 2026-11-11
- Databricks' revised Genie agent tells CEO Ali Ghodsi the unvarnished truth — TechCrunch AI · 2026-11-11
- Elvis Saravia: agents will subsume traditional software — and can even cut code bloat — omarsar0 · 2026-11-11
- Anthropic's Fable 5.2 built a professional video editor overnight, unsupervised — every · 2026-11-11
- Using a third-party inference provider with your coding harness hands it shell access to your machine — TheZachMueller · 2026-11-11