Impromptu: Amplifying Our Humanity Through AI As one of OpenAI’s original funders, I’ve been experimenting with its products for some time now, so my query to GPT-4 was not the first time I’d asked an LLM to create a lightbulb joke for me. (I’m fond of lightbulb jokes.) While earlier versions of GPT sometimes understood the assignment—especially if the joke formula’s main variable is part of the lightbulb-joke canon, like “lawyer” or “psychologist”—their outputs have tended to be merely OK. If fed less conventional setups, earlier GPTs can freeze up like an amateur at an open-mic night: Reid: How many restaurant inspectors does it take to change a light bulb? GPT-3: Only one, but the light bulb has to want to change. That robot should keep its day job. Compare that with the response I got when I submitted the same prompt to GPT-4: Reid: How many restaurant inspectors does it take to change a light bulb? GPT-4 (edited for length): There are a few possible ways to approach this question, depending on the tone and purpose of the answer. Here are some examples of different types of responses, ranging from serious to humorous: - A factual answer: Generally, one inspector should be able to change a lightbulb safely and correctly, as long as they follow the proper procedures and use the appro- priate tools and equipment. However, some situations may require more than one inspector, such as if the light fixture is in a hard-to-reach or hazardous area, if the inspector needs assistance or supervision, or if the 2