# What is a System One model?

A System One model answers a question you define about some input by picking from answers you set in advance, and returns a probability with its pick instead of writing text. TypeSafe AI introduced the term with its first such model, Jev, in a [launch post dated September 15, 2026](https://typesafe.ai/blog/introducing-system-one-models-and-jev), borrowing Kahneman's name for fast, intuitive thinking.

The difference is the training target. TypeSafe's [AI primer](https://docs.typesafe.ai/introduction/machine-learning-primer.md) contrasts RLHF, which trains a model toward responses people prefer, with its own method, reinforcement learning for calibrated decisions (RLCD), which aims for answers given 0.8 to be right about 80% of the time. That's what lets code act on the number: above a threshold, proceed, and below it, hand the case to a person or a reasoning model. An LLM's self-reported confidence [tends to bunch near the top of the scale](/answers/llm-as-judge/does-llm-judge-know-when-unsure), which makes the same threshold hard to place.

The primer also names the limit: calibration describes groups of predictions, so any single high-confidence answer can still be wrong. An [independent test](https://github.com/scienthoon/jev-ood-calibration) found a wider gap off-distribution: on a question whose answer wasn't in the text, Jev's picks averaged 0.74 probability and were right 44.7% of the time.

---

Sources:
- TypeSafe AI, "Introducing System One Models & Jev" (September 15, 2026): https://typesafe.ai/blog/introducing-system-one-models-and-jev (fetched 2026-09-21)
- TypeSafe docs, AI primer (RLHF vs RLCD, calibration): https://docs.typesafe.ai/introduction/machine-learning-primer.md (fetched 2026-09-21)
- TypeSafe docs, System One: https://docs.typesafe.ai/concepts/system-one.md (fetched 2026-09-21)
- scienthoon, jev-ood-calibration (independent calibration test, GitHub): https://github.com/scienthoon/jev-ood-calibration (fetched 2026-09-21)

Source: https://tessary.ai/answers/system-one-models/what-is-a-system-one-model
More on System one models: https://tessary.ai/answers/system-one-models
From Tessary, agent reliability for AI agents in production: https://tessary.ai