I don't understand what makes these different. Are they using custom data sources, or is the only difference the starting prompt that the creator made to tall ChatGPT how to respond to answers?
This blog says that a custom OpenAI gpt consists of:
Behavior: You can give it a detailed set of instructions to guide its answers.
Knowledge base: You can add your own company files for the AI to draw information from.
Capabilities: You can use either OpenAI's existing capabilities (like DALL·E, Browse with Bing, or Data Analysis) or your custom capabilities (other actions the AI can perform).
Behavior: You can give it a detailed set of instructions to guide its answers.
Knowledge base: You can add your own company files for the AI to draw information from.
Capabilities: You can use either OpenAI's existing capabilities (like DALL·E, Browse with Bing, or Data Analysis) or your custom capabilities (other actions the AI can perform).
https://zapier.com/blog/gpt-assistant/