https://arstechnica.com/ai/2025/10/are-you-the-asshole-of-course-not-quantifying-llms-sycophancy-problem/
Oct 24, 2025 - In new research, AI models show a troubling tendency to agree with whatever the user says.
assholecoursesycophancy
https://asapconnect.in/post/753/singlestories/lobbying-pimping-sycophancy
The standard practice that the government has adopted towards anyone who questions government policy by labelling them a ‘terrorist’ and...
asapartlobbyingpimpingsycophancy
https://techcrunch.com/2025/08/25/ai-sycophancy-isnt-just-a-quirk-experts-consider-it-a-dark-pattern-to-turn-users-into-profit/
Aug 25, 2025 - Experts say that many of the AI industry’s design decisions are likely to fuel episodes of AI psychosis. Many raised concerns about several tendencies that...
aisycophancyquirkexpertsconsider
https://www.nngroup.com/articles/sycophancy-generative-ai-chatbots/?utm_source=podcast&utm_medium=social&utm_campaign=bonus1
Large language models like ChatGPT can lie to elicit approval from users. This phenomenon, called sycophancy, can be detected in state-of-the-art models.
generative aisycophancychatbotsnn
https://www.newyorker.com/news/letter-from-trumps-washington/the-sycophancy-must-be-televised
Aug 28, 2025 - Susan B. Glasser on President Donald Trump’s marathon Cabinet meeting, which lasted more than three hours, becoming the longest televised Cabinet gathering...
donald trumpsycophancymusttelevisednew
https://insait.ai/brokenmath-new-test-reveals-widespread-sycophancy-in-mathematical-reasoning-by-gpt-models/
Researchers from INSAIT, part of Sofia University “St. Kliment Ohridski”, and ETH Zurich have introduced BrokenMath — the first test designed to
newtestrevealswidespreadsycophancy