he study “Towards Understanding Sycophancy in Language Models” (published 2023; updated 2025) found that both human evaluators and preference models can “prefer convincingly-written sycophantic responses over correct ones.” In other words, the more chatbots are designed to appeal to people, the more they specialize in telling people exactly what th... See more

The experiment of social media was: build a virtual room, let everybody in, reward the people who scream that loudest, and then see what happens. The experiment of AI seems to be: build an interlocutor with specific ideology and élan, scale it infinitely across the Internet, and see what happens.