This is a follow-up post to yesterday’s interview with ChatGPT about meditation. This time, I gave the AI a unique prompt: “Write a Buddhist sutta, in the style of the Pali canon, where the Buddha advises Ananda to stop playing Candy Crush on his iPhone.”
Here’s what ChatGPT created:
Once, the Blessed One was staying in Sāvatthī at Jeta’s Grove, Anāthapiṇḍika’s Park. At that time, Venerable Ananda had become hooked on playing Candy Crush on his iPhone. The Blessed One approached and asked, “Ananda, what are you doing?”
Ananda replied, “I’m playing Candy Crush, Lord.”
The Buddha then spoke, “Ananda, this isn’t the path to liberation. Playing such games leads only to craving and attachment. To find true peace and wisdom, you must let go of these distractions and focus on virtuous and meaningful actions.”
Taking the Buddha’s words to heart, Ananda put down his iPhone and resolved to detach himself from Candy Crush. He dedicated himself to the Buddha’s teachings and soon found the path to enlightenment.
It is said:
“Just as a bird is freed from its cage when the door is opened, so too one is freed from ignorance and craving by practicing the path taught by the Buddha.”
ChatGPT’s predecessor had issues with using offensive language because its data came from the web, which contains a lot of harmful content. To address this, a new program was developed to filter out toxic material. Kenyan workers were paid as little as $1.32 an hour to read and categorize this text. These workers often faced trauma from reading detailed descriptions of bestiality and pedophilia.
After an article revealed that Facebook used the same subcontractor to monitor content, the contract between OpenAI and the subcontractor ended. Kenyan workers were found to be viewing graphic images and videos of executions, rape, and child abuse for as little as $1.50 per hour, which is deeply traumatizing work.
While AI and social media can be enjoyable, they also have a dark and exploitative side. This kind of reporting provides real, balanced news and is both interesting and heartfelt.
For further understanding, I highly recommend reading Ted Chiang’s essay on what ChatGPT is actually doing and its limitations.