- When you prompt an artificial intelligence chatbot, like ChatGPT, you’re giving it context. What type of information do you want? In what tone should the bot respond? How should the response be edited to better fit what you’re looking for? All of this is just piles of context that you continuously have to provide and refine when working with chatbots. - I was glad to see someone else talking about this. I’ve found it increasingly hard to use ChatGPT because it requires *constant* contextualization for an appropriate output. - In [[Wattenberger, Amelia - Why Chatbots Are Not the Future|‘Why Chatbots Are Not the Future’]], Amelia Wattenberger argues that contextualization features should be built into the interface; different tools can have different inputs for the type of response you’re looking for. - Ultimately, this is just one reason [[{6.3} chatbots are not the right interface for AI]].