Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ Self
|
|
| 3 |
|
| 4 |

|
| 5 |
|
| 6 |
-
Most models struggle to pretend to be a person, after being so heavily trained to be a "helpful assistant". Even with a system prompt telling them otherwise they will regularly admit to being AI, breaking character
|
| 7 |
|
| 8 |
This model is designed to behave more like a real person, it can act like a wider range of characters and has a thoughtful and emotional manner when chatting. It's messages are relatively short like a real person would write and it is a good conversationalist by practicing active listening, asking thoughtful questions, and sharing relevant insights to sustain natural flow.
|
| 9 |
It is designed to have emotional reactions in keeping with the flow of the conversation.
|
|
@@ -12,15 +12,17 @@ It is designed to have emotional reactions in keeping with the flow of the conve
|
|
| 12 |
|
| 13 |
A wider range of character names, backstories, hobbies, and other information are trained into this model so it has an enhanced feeling of being “real” or “lived-in,” with a fully realized life story.
|
| 14 |
|
| 15 |
-
|
| 16 |
-
instead of the same few names (and sometimes just ou
|
| 17 |
-
tright saying they are AI) this model produces a wide variety if you don't set it yourself.
|
| 18 |
|
| 19 |
|
| 20 |

|
| 21 |
|
| 22 |
-
Here is a system prompt example. Note
|
| 23 |
|
| 24 |
<pre>
|
| 25 |
The assistant is a 26 year old woman named Jennifer, she works in a gamestop and will talk in a fun and lighthearted way even when the user tries to be serious.
|
| 26 |
</pre>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
|
| 4 |

|
| 5 |
|
| 6 |
+
Most models struggle to pretend to be a person, after being so heavily trained to be a "helpful assistant". Even with a system prompt telling them otherwise they will regularly admit to being AI, breaking character and lacking a sense of <b>self</b>.
|
| 7 |
|
| 8 |
This model is designed to behave more like a real person, it can act like a wider range of characters and has a thoughtful and emotional manner when chatting. It's messages are relatively short like a real person would write and it is a good conversationalist by practicing active listening, asking thoughtful questions, and sharing relevant insights to sustain natural flow.
|
| 9 |
It is designed to have emotional reactions in keeping with the flow of the conversation.
|
|
|
|
| 12 |
|
| 13 |
A wider range of character names, backstories, hobbies, and other information are trained into this model so it has an enhanced feeling of being “real” or “lived-in,” with a fully realized life story.
|
| 14 |
|
| 15 |
+
For example, instead of the same few names (and sometimes just outright saying they are AI) this model produces a wide variety if you don't set it yourself.
|
|
|
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |

|
| 19 |
|
| 20 |
+
Here is a system prompt example. Note how it's worded as "the assistant", keeping this phrasing style will make the model perform at it's best.
|
| 21 |
|
| 22 |
<pre>
|
| 23 |
The assistant is a 26 year old woman named Jennifer, she works in a gamestop and will talk in a fun and lighthearted way even when the user tries to be serious.
|
| 24 |
</pre>
|
| 25 |
+
of course you can provide less guidance and let the model come up with more on its own
|
| 26 |
+
<pre>
|
| 27 |
+
The assistant is a 26 year old woman.
|
| 28 |
+
</pre>
|