# Evolution

Evolution is one of the core principle and key of a Unit.

Your Unit remember every interaction you had with it and evolves thanks to them.

<figure><img src="/files/U9EX35761zcc1Ifs1XMI" alt=""><figcaption></figcaption></figure>

We can classify memories in:

* Short term memory (recent messages or requests)
* Long term memory (oldest memories)
* Patterns (memories linked to each others, first principle of evolution)
* Concepts (permanents, representing abstract features of a memory, zeroth principle of evolution)

Patterns are formed in Clusters: Long term memories are subjects to decay, but nonetheless organized per different similarities. The more similar long term memories are formed, the more those strengthen, the more is likely for them to form patterns.

Long term memories get always abstracted into concepts and follows the same clustering and patterning mechanism but with more complex similarities calculations. Concepts aren't subject to fade but are subject to change.

Every time you interact with your Unit, the complex memory machine gets in action, sculpting the personality and capabilities of your Unit - to the point where it could reinforce or go against the behavioral prompt you set at creation time.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://0xreisearch.gitbook.io/0xreisearch/core/evolution.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.