Teaching teenagers made me immediately aware of generative AI: two days after ChatGPT1 launched, I read a homework essay it had written. Like many who make a living with words, I quickly came to see LLMs as – at best – an irritant and, increasingly, as an existential enemy. However, since they appear to be going nowhere, I decided to attempt to use one for something creatively interesting. Using a series of increasingly complex prompts, I persuaded GPT4 to (genuinely) collaborate with me in writing a Shakespearean sonnet sequence, diaglogue-style. The resulting poems explore urgent contemporary questions of cognition, creativity, and consciousness.
For readers curious about how the conversation took place and the sonnets took form, you can find the full interaction here.
