Live data from Hacker News

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

github.com

61–70 of 560 posts

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

#61

Earlier quoted context omitted.

Sure but different people have different preferences. Some people mourn replacement of GPT4 with 5 because 5 has way less of a bubbly personality.

I, for one, say good riddance to it.

But it doesn’t say ima good boy anymore :(

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

#63
post #9

Not Claude but ChatGPT - I asked it to pipe down on exactly that kind of response. And it did.

I've done this in my Claude settings, but it still doesn't seem that keen on following it: > Please be measured and critical in your response. I appreciate the enthusiasm, but I highly doubt everything I say is “brilliant” or “astute”, etc.! I prefer objectivity to sycophancy.

Too much context tokens.

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

#64
post #35

Yeah because I am sure if they told you how stupid and wrong you’re, people will continue to use it. It’s superficial but not sure why people get so annoyed about it. It’s an artifact. If devs truly want a helpful coding AI based on real devs doing real work, you’d basically opt for telemetry and allow Anthropic/OpenAI to train on your work. That’s the only way. Otherwise we are at the mercy of “devs” these companies…

> Yeah because I am sure if they told you how stupid and wrong you’re, people will continue to use it.

Are sycophant and jerk the only two options?

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

#65
post #16

GPT-5 has used the phrase "heck yes!" a handful of times to me so far. I quite enjoy the enthusiasm but its not a phrase you hear very often.

I’m getting “oof” a lot.

“Oof (emdash) that sounds like a real issue…”

“Oof, sorry about that”

Etc

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

#66
post #48

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 have learnt to not ask leading questions. Always phrase questions in a neutral way and ask for pro/con analysis of each option.

But then it makes an obvious mistake and you correct it and it says "you are absolutely right". Which is fine for that round but you start doubting whether its just sycophancy.

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

#67
post #9

Not Claude but ChatGPT - I asked it to pipe down on exactly that kind of response. And it did.

GPT-5 ends every single response with something like. > If you’d like, I can demonstrate… or > If you want… and that's /after/ I put in instructions to not do it.

It's weird that it does that given that the leaked system prompt explicitly told it not to.

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

#68

sidenote observation - it seems username "anthropic" on github is taken by a developer from australia more than a decade ago, so Anthropic went with " https://github.com/anthropics/ " with an 's' at the end :)

Ahhh. Thank you! I reported a vscode extension because I thought it was phishing. In my defence they made zero effort to indicate that it was the official extension.

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

#70
post #9

Not Claude but ChatGPT - I asked it to pipe down on exactly that kind of response. And it did.

Yet I'll tell it 100 times to stop using em dashes and it refuses.

What kind of monster would tell a LLM to avoid correct typography?
Post reply on HN