[KongchangAI]
ConceptSystem 1

System One

A cognitive psychology concept originating from Daniel Kahneman's Thinking, Fast and Slow, referring to fast, intuitive, automatic cognitive processes. In the AI field it has been adopted by TypeSafe to define a category of high-frequency, low-complexity specialized decision models within an agent, contrasted with System Two (frontier large models that generate complex text and perform multi-step reasoning).

Timeline (last 90 days)

Oct 14

The derivation gap appeared in all seven judge models the researchers evaluated, including the System One series' CLM and Jev.

Unverified50%
Oct 13

System One scoring typically refers to a fast score given in a single forward pass, without involving multi-step reasoning, self-reflection or chain-of-thought.

Unverified50%
Oct 13

Commit #18976 supports System One scoring on top of the shared state cache, and adds Kev-specific resource limits.

Unverified50%
Oct 12

The concepts of System One and System Two come from Daniel Kahneman's Thinking, Fast and Slow; TypeSafe borrows the concept to distinguish two model invocation paths within an agent.

Unverified50%
Oct 4

In the previous implementation, Ollama determined the scheduling of System One requests by matching the Qwen architecture and its renderer metadata.

Unverified50%
Oct 4

The new version requires that a model must explicitly possess the decision capability before it can be scheduled to handle System One requests.

Unverified50%
Oct 3

eu/jev claims to be the first Jev-class (System One) model fully hosted within the EU and compliant with GDPR requirements.

Unverified50%
Oct 1

The System One model borrows from the dual-system theory in psychology, representing an intuitive, fast decision-making mode, in contrast to the deliberate System Two

Unverified50%
Oct 1

Document processing can adopt a division-of-labor collaborative mode: using lightweight, fast System One models for high-frequency basic judgments, and reserving heavy inference resources for complex tasks

Unverified50%
Oct 1

The System One model excels at four types of document tasks that require rapid decision-making: orientation detection, language detection, classification, and splitting

Unverified50%

4 more timeline events

All Facts (13)

Unverified

The derivation gap appeared in all seven judge models the researchers evaluated, including the System One series' CLM and Jev.

50%
Unverified

System One scoring typically refers to a fast score given in a single forward pass, without involving multi-step reasoning, self-reflection or chain-of-thought.

50%
Unverified

Commit #18976 supports System One scoring on top of the shared state cache, and adds Kev-specific resource limits.

50%
Unverified

The concepts of System One and System Two come from Daniel Kahneman's Thinking, Fast and Slow; TypeSafe borrows the concept to distinguish two model invocation paths within an agent.

50%
Unverified

In the previous implementation, Ollama determined the scheduling of System One requests by matching the Qwen architecture and its renderer metadata.

50%
Unverified

The new version requires that a model must explicitly possess the decision capability before it can be scheduled to handle System One requests.

50%
Unverified

eu/jev claims to be the first Jev-class (System One) model fully hosted within the EU and compliant with GDPR requirements.

50%
Unverified

Document processing can adopt a division-of-labor collaborative mode: using lightweight, fast System One models for high-frequency basic judgments, and reserving heavy inference resources for complex tasks

50%
Unverified

The System One model excels at four types of document tasks that require rapid decision-making: orientation detection, language detection, classification, and splitting

50%
Unverified

The System One model borrows from the dual-system theory in psychology, representing an intuitive, fast decision-making mode, in contrast to the deliberate System Two

50%
Unverified

Jev is an open-source System One lightweight model designed to handle rapid document decision-making tasks

50%
Unverified

System One models generally refer to lightweight models with relatively few parameters, shorter reasoning chains, and extremely low response latency, in contrast to slow-thinking reasoning models such as o1 and DeepSeek-R1.

50%
Unverified

TypeSafe officially defines Jev as the first model in the "System One" category.

50%

Source Articles