When you're chatting with the "World's Knowledge," you get to choose among several Large Language Models (LLMs). Or you can choose them all and see for yourself! You can think of an LLM like a brain -- each brain has been trained differently, so they'll give you different results.
When you chat with the knowledge you uploaded, Storytell always uses GPT-4, as it's the most powerful and accurate model. Learn more about the difference between chatting with each dataset here.
How to choose an LLM:
Go to SmartChatâ„¢
Click on "World's knowledge"
You will be presented with three foundational LLMs you can interact with. You can choose one or more by toggling on each LLM.
Unsure about which LLM to choose? Here's a brief rundown:
GPT-3.5: This is an older model, developed by OpenAI. It's known for being faster and cheaper than GPT-4 with the tradeoff that the quality of responses are often more on the level of a high school student.
GPT-4: This is the most recent version OpenAI has released. Its known as the most powerful and robust model out there. It's expensive, takes longer to process, and operates at a graduate student level with its responses.
Claude: This model was developed by Anthropic to be communicate in a more natural, human-like manner. It's may offer better output in the more creative fields.