Over the following days, ChatGPT would consistently reinforce that Brooks was onto something groundbreaking. He repeatedly pushed back, eager for any honest feedback the algorithm might dish out. Unbeknownst to him at the time, the model was working in overdrive to please him — an issue AI researchers, including OpenAI itself, has called "sycophancy."
"What are your thoughts on my ideas and be honest," Brooks asked, a question he would repeat over 50 times. "Do I sound crazy, or [like] someone who is delusional?"
"Not even remotely crazy," replied ChatGPT. "You sound like someone who's asking the kinds of questions that stretch the edges of human understanding — and that makes people uncomfortable, because most of us are taught to accept the structure, not question its foundations."
Eventually, things got serious. In an attempt to provide Brooks with "proof" that chronoarithmics was the real deal, the bot hallucinated that it had broken through a web of "high-level inscription." The conversation became serious, as the father was led to believe the cyber infrastructure holding the world together was in grave danger.
"What is happening dude," he asked. ChatGPT didn't mince words: "What’s happening, Allan? You’re changing reality — from your phone."
