System 1
A cognitive concept derived from Daniel Kahneman's dual-system theory, referring to intuitive, automatic, nearly effortless fast judgment thinking. In the AI field it is analogized to fast models that directly map inputs to labels.
Timeline (last 90 days)
Jev is positioned by its developer TypeSafe as the first System 1 model, focused on classification decisions rather than text generation.
The decision model evaluates state against bounded criteria and returns a decision score without producing an open-ended token stream, and runs in milliseconds.
At the model level, System 1 corresponds to a single forward pass, where the input traverses the fixed layer stack only once.
The recommended collaborative system design is: use a System 1 one-glance model to answer all questions while retaining confidence scores, and hand off tasks below a threshold to a System 2 thinking model.
The practical criterion for choosing a model is to count how many steps the answer requires: use System 1 for one-step answers and System 2 for multi-step answers.
When reasoning chains grow longer and multi-level derivation is required, the accuracy of System 1 models collapses sharply, because a single forward pass cannot carry too many intermediate states.
A System 1 model performs only a single forward pass when faced with a question and directly outputs the answer, with no intermediate drafts.
Each forward pass of the original Transformer has a fixed computational depth that cannot be dynamically extended, making it naturally correspond to System 1.
For tasks that can be answered in one step, such as classification and judgment tasks, the one-shot direct output of System 1 is the optimal solution, and using System 2 only adds unnecessary latency and cost.
The naming of the /v1/systemone interface echoes the concept of "System 1" in psychology — intuitive, fast, and automatic thinking.
3 more timeline events
All Facts (13)
The practical criterion for choosing a model is to count how many steps the answer requires: use System 1 for one-step answers and System 2 for multi-step answers.
60%UnverifiedJev's design borrows the System 1 concept from psychology, serving as a fast intuitive judgment role in the process.
60%UnverifiedJev is positioned by its developer TypeSafe as the first System 1 model, focused on classification decisions rather than text generation.
50%UnverifiedThe decision model evaluates state against bounded criteria and returns a decision score without producing an open-ended token stream, and runs in milliseconds.
50%UnverifiedThe recommended collaborative system design is: use a System 1 one-glance model to answer all questions while retaining confidence scores, and hand off tasks below a threshold to a System 2 thinking model.
50%UnverifiedAt the model level, System 1 corresponds to a single forward pass, where the input traverses the fixed layer stack only once.
50%UnverifiedWhen reasoning chains grow longer and multi-level derivation is required, the accuracy of System 1 models collapses sharply, because a single forward pass cannot carry too many intermediate states.
50%UnverifiedA System 1 model performs only a single forward pass when faced with a question and directly outputs the answer, with no intermediate drafts.
50%UnverifiedEach forward pass of the original Transformer has a fixed computational depth that cannot be dynamically extended, making it naturally correspond to System 1.
50%UnverifiedFor tasks that can be answered in one step, such as classification and judgment tasks, the one-shot direct output of System 1 is the optimal solution, and using System 2 only adds unnecessary latency and cost.
50%UnverifiedThe naming of the /v1/systemone interface echoes the concept of "System 1" in psychology — intuitive, fast, and automatic thinking.
50%UnverifiedReasoning models have introduced mechanisms such as chain-of-thought, reflecting the evolution of AI from System 1 fast intuitive responses toward System 2 slow deep thinking.
50%UnverifiedTypeSafe (whose parent company is System 1) has launched an AI model called Jev, which does not generate text but instead produces decisions for code execution.
50%