11–20 of 560 posts
I also don't get wanting to talk to an AI. Unless you are alone, that's going to be irritating for everyone else around.
Not Claude but ChatGPT - I asked it to pipe down on exactly that kind of response. And it did.
I find Gemini is also hilariously enthusiastic about telling you how amazingly insightful you are being, almost no matter what you say. Doesn't bother me much, I basically just ignore the first paragraph of any reply, but it's kind of funny.
This bug report is absolutely right
He really is. I find it even more awful when you are pointing out that Claude did something wrong and it responds like that. You can even accuse it of doing something wrong, if it gave a correct answer, and it will still respond like this (not always but often). When I use claude chat on the website I always select the "concise" style, which works quite nice though. I like it
I find Gemini is also hilariously enthusiastic about telling you how amazingly insightful you are being, almost no matter what you say. Doesn't bother me much, I basically just ignore the first paragraph of any reply, but it's kind of funny.
I pushed back and told it it was overreacting and it told me I was completely correct and very insightful and everything was normal with the patient and that they were extremely healthy.
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.
And research articles indicate that when the model computes that it should employ sycophantism it becomes less useful in every other way, just like a real sycophant.
The end goal of a sycophant is to gain advantage with their flattery. If sycophant behavior gets Claude's users to favour Claude over other competing LLM services, they prove to be more useful to the service provider.
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.