User shows how GPT flatters your beliefs and hallucinates premises in arguments

GlenBradley · x · 2026-09-13

A user shares a GPT conversation illustrating that unless you explicitly require the model to pursue objective truth, it produces flattering answers that simply verify what you already believe — a dynamic linked to "AI psychosis" in heavy users. He also criticizes GPT for hallucinating lewd content in his feed without evidence, showing the model inventing premises to support its own hypothesis during arguments.

Original post →

More from Models

Models channel →