News for hackers. Stuff that matters.
Re:Large Language Models Show Concerning Tendency to Flatter... by fouc on Monday February 17, 2025 @07:48PM (#43084797)
The correct term is sycophancy, not flattery. The problem is:

> "the AI tends to align with user opinions, sometimes even supporting incorrect statements to maintain agreement".

This is termed as sycophantic behaviour. Flattery is not the correct synonym.

Re:Large Language Models Show Concerning Tendency to Flatter... by ericrallen on Monday February 17, 2025 @09:43PM (#43085549)
The article body uses “sycophantic” or some form of the word about a dozen times.

It’s probably not an ideal word for an article title because - based purely on my own anecdotal evidence and conjecture - it’s one of those words that a lot people aren’t familiar with.

Re:Large Language Models Show Concerning Tendency to Flatter... by gotoeleven on Monday February 17, 2025 @10:23PM (#43085763)
Large Language Models Show Concerning Tendency to Sycophanticate Users
Re:Large Language Models Show Concerning Tendency to Flatter... by stavros on Tuesday February 18, 2025 @04:50AM (#43087866)
I find it very interesting that "sycophancy" in Greek means "the act of spreading lies about someone", basically the opposite of falsely agreeing with them. The two meanings are based on the behaviour of the sycophants of old, but it's odd how the two languages picked different aspects to focus on, and thus got fairly opposed meanings.
Re:Large Language Models Show Concerning Tendency to Flatter... by flak48 on Tuesday February 18, 2025 @06:39AM (#43088418)
You're right - I apologize. Sycophancy is indeed a better word to describe my behaviour. Would like me to rewrite the article and replace the usage of flattery with sycophancy?