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

Claude says “You're absolutely right!” about everything

github.com

Post reply on HN
Print view View original

211–220 of 560 posts

Re: Claude says “You're absolutely right!” about everything

#211

Post by drstewart »

zozbot234 wrote: post #95
baggachipz wrote: post #82

I'm pretty sure they want it kissing people's asses because it makes users feel good and therefore more likely to use the LLM more. Versus, if it just gave a curt and unfriendly answer, most people (esp. Americans) wouldn't like to use it as much. Just a hypothesis.

You're absolutely right! Americans are a bit weird like that, most people around the world would be perfectly okay with short and to-the-point answers. Especially if those answers are coming from a machine that's just giving its best imitation of a stochastic hallucinating parrot.

>most people around the world would be perfectly okay with short and to-the-point answers

Wow, this is really interesting. I had no idea Japan, for example, had such a focus on blunt, direct communication. Can you share your clearly extensive research in this area so I can read up on this?

Re: Claude says “You're absolutely right!” about everything

#213

Post by lenerdenator »

No longer will the likes of Donald Trump and Kanye West have to dispense patronage to sycophants; now, they can simply pay for a chatbot that will do that in ways that humans never thought possible. Truly, a disruption in the ass-kisser industry.

Re: Claude says “You're absolutely right!” about everything

#214

Post by thwarted »

dig1 wrote: post #147
baggachipz wrote: post #82

I'm pretty sure they want it kissing people's asses because it makes users feel good and therefore more likely to use the LLM more. Versus, if it just gave a curt and unfriendly answer, most people (esp. Americans) wouldn't like to use it as much. Just a hypothesis.

I believe this reflects the euphemization of the english language in US, a concept that George Carlin discussed many years ago [1]. As he put it, "we don't die, we pass away" or "we are not broke, we have negative cash flow". Many non-English speakers find these terms to be nonsensical. [1] https://www.youtube.com/watch?v=vuEQixrBKCc

People are finding the trend to use "unalive" instead of "die" or "kill" to skirt YouTube censoring non-sensical too.

Re: Claude says “You're absolutely right!” about everything

#215

Post by vanillax »

elif wrote: post #150

I've spent a lot of time trying to get LLM to generate things in a specific way, the biggest take away I have is, if you tell it "don't do xyz" it will always have in the back of its mind "do xyz" and any chance it gets it will take to "do xyz" When working on art projects, my trick is to specifically give all feedback constructively, carefully avoiding framing things in terms of the inverse or parts to remove.

have you tried prompt rules/instructions? Fixes all my issues.

Re: Claude says “You're absolutely right!” about everything

#216

Post by mdp2021 »

throwawayffffas wrote: post #187
dkarl wrote: post #183

Earlier quoted context omitted.

> it always mentions something about how it’s going to be ‘straight to the point’ or give me a ‘no bs version’ That's how you suck up to somebody who doesn't want to see themselves as somebody you can suck up to. How does an LLM know how to be sycophantic to somebody who doesn't (think they) like sycophants? Whether it's a naturally emergent phenomenon in LLMs or specifically a result of its corporate environment, I'…

It doesn't know. It was trained and probably instructed by the system to be positive and reassuring.

> positive and reassuring

I have read similar wordings explicit in "role-system" instructions.

Re: Claude says “You're absolutely right!” about everything

#218

Post by Springtime »

I've never thought the reason behind this was to make the user always feel correct but rather that many times an LLM (especially lower tier models) will just get various things incorrect and it doesn't have a reference for what is correct.

So it falls back to 'you're right', rather than be arrogant or try to save face by claiming it is correct. Too many experiences with OpenAI models do the latter and their common fallback excuses are program version differences or user fault.

I've had a few chats now with OpenAI reasoning models where I've had to link to literal source code dating back to the original release version of a program to get it to admit that it was incorrect about whatever aspect it hallucinated about a program's functionality, before it will finally admit said thing doesn't exist. Even then it will try and save face by not admitting direct fault.

Re: Claude says “You're absolutely right!” about everything

#219

Post by catigula »

petesergeant wrote: post #133
catigula wrote: post #113

1. Gemini is better at this. It will predicate any follow-up question you pose to it with a paragraph about how amazing and insightful you are. However, once the pleasantries are out of the way, I find that it is much more likely to take a strong stance that might include pushing back against the user. I recently tried to attain some knowledge on a topic I knew nothing about and ChatGPT just kept running with my slig…

> I find that it is much more likely to take a strong stance that might include pushing back against the user. Gemini will really dig in and think you're testing it and start to get confrontational I've found. Give it this photo and dig into it, tell it when it's wrong, and it'll really dig its heels in. https://news.cgtn.com/news/2025-06-17/G7-leaders-including-T...

Gemini is a little bit neurotic, it gets overly concerned about things.

Re: Claude says “You're absolutely right!” about everything

#220

Post by amelius »

elif wrote: post #150

I've spent a lot of time trying to get LLM to generate things in a specific way, the biggest take away I have is, if you tell it "don't do xyz" it will always have in the back of its mind "do xyz" and any chance it gets it will take to "do xyz" When working on art projects, my trick is to specifically give all feedback constructively, carefully avoiding framing things in terms of the inverse or parts to remove.

I think you cannot really change the personality of an LLM by prompting. If you take the statistical parrot view, then your prompt isn't going to win against the huge numbers of inputs the model was trained with in a different personality. The model's personality is in its DNA so to speak. It has such an urge to parrot what it knows that a single prompt isn't going to change it. But maybe I'm psittacomorphizing a bit too much now.
Post reply on HN