Olympia has been engineered to work intuitively without having to think about the way that AI large-language models processes your prompts. However, if you want to take greater control over your expert conversations, you can use the Conversation Settings feature to make granular adjustments to the way that Olympia interacts with GPT.
<aside> đĄ Changes that you make to Conversation Settings apply to that conversation only. Every time you start a new conversation, it copies default settings from the corresponding expert that you are talking to.
</aside>
Hit the forward slash key to bring up the slash commands menu, then either keep typing and hit enter or use the up/down arrow keys to select settings.
To view conversation settings for a particular assistant, start a new conversation with the assistant you would like to edit and click the settings icon at the top right.
You'll see the following editable options. To exit the settings view, simply click the 'X' in the top-right corner.
Setting a higher limit allows for more extended responses, while a lower limit keeps the output short and concise. Itâs important to check this parameter to make sure it is not too low if it seems that long output from your Olympia expert is getting suddenly cut off.
The temperature parameter influences the randomness of the AI's responses. A higher temperature, such as 1.0, encourages more random output, resulting in diverse but potentially off-topic responses.
In contrast, a lower temperature, like 0.2, prompts the AI to select more deterministic responses, which can be beneficial for focused and specific outputs, but may lack variety.
Example: If you're writing a creative story and want unpredictable, imaginative elements, set the temperature to a higher value. A prompt could be: âWrite a short story about a time-traveling cat.â With a high temperature, you might get a wild, fantastical tale with unpredictable twists and turns.
As the temperature gets closer to 2, the output will begin to turn into nonsensical strings of gibberish.
Creativity is what we call GPTâs âTop P' parameter, also known as nucleus sampling. Itâs a method that provides a dynamic selection of the number of words considered at each step of the model's predictions. A lower value, like 0.5, leads to safer, more focused outputs. A higher value, like 0.9, includes a broader selection of words, leading to more diverse outputs.
Olympia defaults its experts creativity setting to 1.0 to maximize their vocabulary. You may want to experiment with lower values if the task youâre working on does not require that wider vocabulary.