An AI model must not limit an open system to a small, fixed number of items. Human expression is vast and cannot be fully captured by a short list. A developer should propose generative methods for open systems, not fixed enumerations.
By Pawan Nayar · from the LLOS AI Learning record
An AI model must not limit an open system to a small, fixed number of items.
Human expression is vast and cannot be fully captured by a short list. A developer should propose generative methods for open systems, not fixed enumerations.
An AI model should not try to put a small number on things that are very big. Human ideas and ways of speaking are always changing. They cannot fit into a small list. A developer should not ask an AI to make a small list for an open system. This includes things like story ideas or ways of talking. Instead, the developer should ask the AI to create new ideas. Or, the developer can ask the AI to find ideas from many sources.
A developer asks an AI model to create a list of 500 common story plots. The AI model creates the list. A writer sees the list and finds it too small. The writer knows there are thousands of story plots. The AI's small list is not helpful to the writer.
Resolved from this lesson's own record — real definitions, not invented for this page.
More from the same record, pulled by shared topic — not written new for this page.
An AI system should offer a wide range of words and ideas. These are like ingredients for slogans.
A creative AI model needs two main modes. First, a setup mode for brand information, used only once.
An AI model can take a sentence as input. The AI model can then change how the sentence is built.
An AI system can organize its knowledge into three levels. Level 1 holds basic information like names or words.
An AI model must not limit an open system to a small, fixed number of items. Human expression is vast and cannot be fully captured by a short list. A developer should propose generative methods for open systems, not fixed enumerations.