Hacker News Reader

Comment by shubhamjain | Hacker News Reader

Geez! When it comes to answering questions, GPT-5 almost always starts with glazing about what a great question it is, where as GPT-4 directly addresses the answer without the fluff. In a blind test, I would probably pick GPT-4 as a superior model, so I am not surprised why people feel so let down with GPT-5.

View on HN

GPT-4 is very different from the latest GPT-4o in tone. Users are not asking for the direct no-fluff GPT-4. They want the GPT-4o that praises you for being brilliant, then claims it will be “brutally honest” before stating some mundane take.

GPT-4 starts many responses with "As an AI language model", "I'm an AI", "I am not a tax professional", "I am not a doctor". GPT-5 does away with that and assumes an authoritative tone.

That makes fundraising easier, by increasing the appearance of authority and therefore coming off as a "better" model. In the elo ratings I'm sure GPT-5 is doing better because of the clear push back against these LLMs as ways to "cheat" without understanding and to flood propaganda -- better not to mention it.

GPT5 only commended the prompt on questions 7, 12, and 14. 3/14 is not so bad in my opinion.

(And of course, if you dislike glazing you can just switch to Robot personality.)

I think that as the models will be further trained on existing data and likely chats sycophancy will keep getting word and worse.

Change to robot mode

Reply on news.ycombinator.com