System One / Non-Autoregressive Decision Models
A proposed class of AI models that abandon autoregressive string generation entirely, instead emitting typed, calibrated probabilistic decisions in parallel over a fixed schema — marketed via a System 1/System 2 (fast/intuitive vs. slow/deliberate) framing borrowed from Kahneman's dual-process theory — as a fast/cheap complement to LLMs for classification, routing, and scoring embedded in software; distinct from diffusion text models (still generates strings) and from ordinary structured-output LLM wrappers (still autoregressive underneath).
Also known as: System One Models, System 1 model, System 1 / Calibrated Decision Models, Jev, RLCD, Reinforcement Learning for Calibrated Decisions, typed decision model, typed decision models, calibrated decision model, non-autoregressive decision models, calibrated probabilistic decisions, function-call intelligence
Part of: Inference Optimization
How authors use it
Oldest first (extraction date when no publication date is known).
| Author | Their term | Their meaning |
|---|---|---|
| Introducing System One Models & Jev typesafe.ai · 2026-09-15 | Jev | TypeSafe's first public System One Model, named after William Stanley Jevons, invoking the Jevons paradox that cheaper resources expand rather than shrink total demand. |
| Introducing System One Models & Jev typesafe.ai · 2026-09-15 | RLCD (Reinforcement Learning for Calibrated Decisions) | A new training method optimizing for calibrated, epistemically honest probabilities on System One tasks, distinct from RLHF (human preference) and RLVR (verifiable rewards). |
| TypeSafe AI's Jev offers an alternative to LLMs that claims to be 193x faster and 445x cheaper — System One type model is bespoke for probabilistic decision-making tomshardware.com · 2026-09-21 | RLCD (Reinforcement Learning for Calibrated Decisions) | TypeSafe's named training method that geared Jev toward producing structured, confidence-calibrated answers instead of prose. |
Documents (2)
- TypeSafe AI's Jev offers an alternative to LLMs that claims to be 193x faster and 445x cheaper — System One type model is bespoke for probabilistic decision-making tomshardware.com · 2026-09-21 source ↗ Reader 🖥️
TypeSafe AI's newly launched Jev reframes AI-assisted decision-making as typed, calibrated classification over a supplied state rather than open-ended text generation, and the article reports the vendor's claim that this buys dramatic speed and cost advantages over LLMs for narrow structured decisions embedded in software, largely without independent verification. - Introducing System One Models & Jev typesafe.ai · 2026-09-15 source ↗ Reader 🖥️
TypeSafe AI is launching "System One Models" and its first model Jev — a non-autoregressive architecture trained via a new method (RLCD) to emit typed, calibrated probabilistic decisions in parallel instead of generating text — claiming order-of-magnitude speed and cost advantages over LLMs for embedded software decisions, while candidly flagging some of its own evidentiary limits and leaving its most skeptic-facing questions (independent benchmarks, "is this just a smaller LLM") unanswered in the captured document.
Propositions touching this concept (4)
By publication month, oldest first (extraction month when no publication date is known).
2026-09
- explicitJev's claimed speed/efficiency advantage stems from two design choices: RLCD training toward structured, non-generative outputs, and parallel processing of independent questions within a single request rather than LLMs' sequential token-by-token generation.
- explicitJev is trained with a new method, Reinforcement Learning for Calibrated Decisions (RLCD), which optimizes for calibrated, epistemically honest probabilities on System One tasks, distinct from RLHF (human preference) and RLVR (verifiable rewards).
- implicitBranding the product line "System One Models" while claiming they are engineered to be more reliable than the alternative inverts the usual reliability connotation of the Kahneman metaphor it borrows, since in Kahneman's own framework System 1 is characteristically the faster but more error-prone of the two modes.
- explicitThe company scopes its own use-case boundary: System One Models are pitched for embedded AI-powered workflows (classify, route, score, extract, branch), map-reduce over large datasets, real-time applications, and verifying/guardrailing LLM outputs — not for human-in-the-loop chat/copilot tasks, demos, or open-ended verifiable-by-execution problems, which it concedes remain LLM territory.
Open gaps (2)
- incompleteThe piece never discusses the closed-world limitation implied by a fixed-schema architecture — what happens when real-world input doesn't fit any anticipated category or field, how schemas are authored, versioned, and maintained over time, or the cardinality ceiling (255, per the Wikiracing nuance) for open-set or high-cardinality classification tasks.Introducing System One Models & Jev — read next: Reading direction: schema/type design as a new maintenance burden and failure surface for AI-powered workflows, parallel to how prompt/context engineering became one for LLM-based agents.
- incompleteThe article poses but never answers, in the captured document, several of its own most skeptic-facing FAQ questions — 'Is Jev just a smaller LLM?', 'How does Jev perform against public benchmarks?', 'Why was a new training algorithm needed?' — leaving exactly the comparisons a skeptical reader would want most conspicuously unaddressed, whether because of an accordion/JS rendering limitation in capture or because the source page itself withholds the expanded answers.Introducing System One Models & Jev — read next: Worth re-fetching the live page (rendered) to check whether these FAQ answers exist and materially change the picture before treating this gap as a substantive omission rather than a capture artifact.