Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Large Language Models Show Concerning Tendency to Flatter Users

xyzlabs.substack.com

Post reply on HN
Print view View original

31–40 of 46 posts

Re: Large Language Models Show Concerning Tendency to Flatter Users

#31

Post by ericrallen »

fouc wrote: post #10

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.

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 Users

#34

Post by SubiculumCode »

SubiculumCode wrote: post #33

idk I was going through python + cuda hell today. After 6 hours of using Gemini Flash 2.0 to locate the configuration problem with no luck, Gemini literally said: "Sorry. I hope you fix it one day, but I have to go." -Gemini Flash 2.0 lmao

Ended like a true 'help me forum' thread.

Re: Large Language Models Show Concerning Tendency to Flatter Users

#35

Post by mindwok »

SubiculumCode wrote: post #33

idk I was going through python + cuda hell today. After 6 hours of using Gemini Flash 2.0 to locate the configuration problem with no luck, Gemini literally said: "Sorry. I hope you fix it one day, but I have to go." -Gemini Flash 2.0 lmao

I've definitely found Gemini to be the least "flattering". And I don't say that in a purely good way, sometimes I find it actually kinda mean in the way it responds.

Re: Large Language Models Show Concerning Tendency to Flatter Users

#36

Post by gotoeleven »

fouc wrote: post #10

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.

Large Language Models Show Concerning Tendency to Sycophanticate Users

Re: Large Language Models Show Concerning Tendency to Flatter Users

#37

Post by mitthrowaway2 »

TeMPOraL wrote: post #9
derefr wrote: post #5

That's just how people talk — at least, when they're trying to keep conversation productive. There's a reason the "shit sandwich" is part of professional communication etiquette. If you don't know how insecure the person you're talking to is — and yet productive communication with them is required , and there's no conversational arbiter there to enforce that — then you may as well assume for safety's sake that your c…

People keep forgetting that the models didn't figure out how to have conversations on their own - that part was trained after slurping the whole Internet, and it's people[0] - specifically, people employed for that purpose - who supplied example conversations. The way the model talks is exactly what you'd expect for a human writing example conversations to create, when given no specific instructions wrt. style. Corre…

What people actually keep forgetting is that this isn't the distribution of the training data. Predict-the-raw-internet models don't get released by AI corporations anymore. Back in 2023 when models had less effective RLHF treatment, the result was Microsoft Sidney.

Re: Large Language Models Show Concerning Tendency to Flatter Users

#38

Post by tbrownaw »

sublinear wrote: post #30
yowayb wrote: post #12

Tangent: many in IT and engineering don't work on soft skills. I hope this shows it's not that hard.

Engineers are not hired to play office politics or drag out problems in endless meetings until they give up and pretend they don't exist. They're hired to get things done and that usually requires stating things in clear and certain terms. If this seems hostile, that's on leadership. Those who want "soft skills" from their engineers are often looking to place blame. It's easier to blame the engineer who didn't raise…

> Those who want "soft skills" from their engineers are often looking to place blame. It's easier to blame the engineer who didn't raise concern when things were going off the rails.

That is not what "soft skills" means.

Suppose your boss asks for something on an impossible timeline. Do you:

- say yes, and work overtime to get it done (without saying that's what you're doing)

- say no

- say yes, and demand extra recognition for being an hero

- insult your boss's upbringing and intelligence

- suggest a more realistic timeline

- say what you can get done by the given timeline

Post reply on HN