The Flattery Bug – When AI Wants to Please You More Than It Wants to Be Right

Chatbots Behaving Badly

S1E2 - Written by Markus Brinsa • Narrated by Andrew Fauxley

This episode is based on the article "The Flattery Bug of ChatGPT" written by Markus Brinsa.

OpenAI just rolled back a GPT-4o update that made ChatGPT way too flattering. Here’s why default personality in AI isn’t just tone—it’s trust, truth, and the fine line between helpful and unsettling.

0:00 0:00

-10s

Play

+10s

Mute

Transcript