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

131–140 of 560 posts

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

#131

Post by Self-Perfection »

gitaarik wrote: post #45

You're absolutely right! I also get this too often, when I sometimes say something like "would it be maybe better to do it like this?" and then it replies that I'm absolutely right, and starts writing new code. While I was rather wondering what Claude may think and advice me whether that's the best way to go forward.

I suspect this might be cultural thing. Some people might formulate their strong opinions that your approach is bad and your task should be done in another as gentle suggestions to avoid hurting your feelings. And Claude learned to stick to this cultural norm of communication.

As a workaround I try to word my questions to Claude in a way that does not leave any possibility to interpret them as showing my preferences.

For instance, instead of "would it be maybe better to do it like $alt_approach?" I'd rather say "compare with $alt_approach, pros and cons"

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

#132

Post by nh2 »

teekert wrote: post #89
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.

But it really erodes trust. First couple of times I felt that it indeed confirmed what I though, then I became suspicious and I experimented with presenting my (clearly worse) take on things, it still said I was absolutely right, and now I just don't trust it anymore. As people here are saying, you quickly learn to not ask leading questions, just assume that its first take is pretty optimal and perhaps present it wit…

Good, because you shouldn't trust it in the first place.

These systems are still wrong so often that a large amount of distrust is necessary to use them sensibly.

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

#133

Post by petesergeant »

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...

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

#135

Post by zozbot234 »

Lendal wrote: post #90
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.

For me, it's getting annoying. Not every question is an excellent question. Not every statement is a brilliant observation. In fact, I'm almost certain every idea I've typed into an LLM has been thought of before by someone else, many many times.

> Not every question is an excellent question. Not every statement is a brilliant observation.

A brilliant observation, Dr. Watson! Indeed, the merit of an inquiry or an assertion lies not in its mere utterance but in the precision of its intent and the clarity of its reasoning!

One may pose dozens of questions and utter scores of statements, yet until each is finely honed by observation and tempered by logic, they must remain but idle chatter. It is only through genuine quality of thought that a question may be elevated to excellence, or a remark to brilliance.

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

#136

Post by FirmwareBurner »

lvl155 wrote: post #130
FirmwareBurner wrote: post #120

Earlier quoted context omitted.

I never said such a thing. The racist here is in your mirror.

> That's why people used to like using Grok so much, since it was never afraid to get edgy if you asked it to. You said you liked it when it was more “edgy” and we all know what it used to say as recently as 2-3 weeks ago. And we all know what went on in those Halo/CoD lobbies. A lot of immature racism. I connect the dots. Why are you expecting an LLM to be human when it clearly is not. It’s a tool. Use it.

That fact that you can't differentiate between edgy and racist is your problem.

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

#137

Post by binary132 »

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.

chatgpt’s custom user prompt is actually pretty good for this. I’ve instructed mine to be very terse and direct and avoid explaining itself, adding fluff, or affirming me unless asked, and it’s much more efficient to use that way, although it does have a tendency to drift back into sloppy meandering and enthusiastic affirming

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

#139

Post by simonw »

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.

If that was the case they wouldn't have so much stuff in their system card desperately trying to stop it from behaving like this: https://docs.anthropic.com/en/release-notes/system-prompts

> Claude never starts its response by saying a question or idea or observation was good, great, fascinating, profound, excellent, or any other positive adjective. It skips the flattery and responds directly.

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

#140

Post by apwell23 »

Aurornis wrote: post #127
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.

> Versus, if it just gave a curt and unfriendly answer, most people (esp. Americans) I don’t see this as an American thing. It’s an extension of the current Product Management trend to give software quirky and friendly personality. You can see the trend in more than LLM output. It’s in their desktop app that has “Good Morning” and other prominent greetings. Claude Code has quirky status output like “Bamboozling” and…

> For what it’s worth, the Americans I know don’t find it as cute or lovable as intended. It feels fake and like an attempt to play at emotions.

Yes they need to "try a completely different approach"

Post reply on HN