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

GPT-5.1: A smarter, more conversational ChatGPT

openai.com

Post reply on HN
Print view View original

741–750 of 766 posts

Re: GPT-5.1: A smarter, more conversational ChatGPT

#741

Post by engeljohnb »

mrguyorama wrote: post #711
thewebguyd wrote: post #181

Earlier quoted context omitted.

Right. I want to be conversational with my computer, I don't want it to respond in a manner that's trying to continue the conversation. Q: "Hey Computer, make me a cup of tea" A: "Ok. Making tea." Not: Q: "Hey computer, make me a cup of tea" A: "Oh wow, what a fantastic idea, I love tea don't you? I'll get right on that cup of tea for you. Do you want me to tell you about all the different ways you can make and enjoy…

Why do you want to talk to your computer? I just want to make it do useful things. I don't spend a lot of time talking to my vacuum or my shoes or my pencil. Even Star Trek did not have the computer faff about. Picard said "Tea, earl grey, hot" and it complied , it did not respond. I don't want a computer that talks. I don't want a computer with a personality. I don't want my drill to feel it's too hot to work that d…

There it is, the most frequent question a hacker has to answer. Why would you want that? The answer's always the same: because it's cool.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#742

Post by DonaldPShimoda »

brookst wrote: post #736
DonaldPShimoda wrote: post #733

Earlier quoted context omitted.

Oh, lord, spare me the corporate apologetics. Releasing a chatbot that confidently states wrong information is bad enough on its own — we know people are easily susceptible to such things. (I mean, c'mon, we had people falling for ELIZA in the '60s!) But to then immediately position these tools as replacements for search engines, or as study tutors, or as substitutes for professionals in mental health? These aren't "…

Ad hom attacks instantly declare “not worth engaging with”.

That's a funny irony: I didn't use an ad hominem in any way, but your incorrect assertion of it makes me come to the same conclusion about you.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#743

Post by Y_Y »

binary132 wrote: post #731
porridgeraisin wrote: post #263

Earlier quoted context omitted.

Yeah. And in general, not taking a potshot at who you replied to, the only people who place citations/peer review on that weird faux-intellectual pedestal are people that don't work in academia. As if publishing something in a citeable format automatically makes it a fact that does not need to be checked for reason. Give me any authoritative source, and I can find you completely contradictory, or obviously falsifiabl…

I was actually just referencing the standard Wikipedia annotation that means something approximately like “you should support this somewhat substantial claim with something more than 'trust me bro'” In other words, 10 pages of LLM blather isn’t doing much to convince me a given answer is actually better.

I approve this message. For the record I'm a working scientist with (unfortunately) intimate knowledge of the peer review system and its limitations. I'm quite ready to take an argument that stands on its own at face value, and have no time for an ipse dixit or isolated demand for rigor.

I just wanted to clarify what I thought was intended by the parent to my comment, especially aince I thought the original argument lacked support (external or otherwise).

Re: GPT-5.1: A smarter, more conversational ChatGPT

#744

Post by wubrr »

brookst wrote: post #735
wubrr wrote: post #603

Earlier quoted context omitted.

I don't know what you're basing your 'minority' and 'most people' claims on, but seems highly unlikely.

You think all of these AI companies with trillions of dollars in investment haven’t thought to do market research? Does that really seem more likely than the idea that the HN population is not representative of the global market?

Apply that logic to any failed startup/company/product that had a lot of investment (there are maaaany) and it should become obvious why it's a very weak and fallacious argument.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#745

Post by larodi »

energy123 wrote: post #515
larodi wrote: post #392

Earlier quoted context omitted.

Can you prove your statement?

Winning gold medals in a bunch of competitions like IMO.

like 20 years ago or even before that? and if so - what does your winning even prove exactly here, save for the fact that it is never late to tap oneself by the shoulder for having done stuff?

Re: GPT-5.1: A smarter, more conversational ChatGPT

#746

Post by binary132 »

Y_Y wrote: post #743
binary132 wrote: post #731

Earlier quoted context omitted.

I was actually just referencing the standard Wikipedia annotation that means something approximately like “you should support this somewhat substantial claim with something more than 'trust me bro'” In other words, 10 pages of LLM blather isn’t doing much to convince me a given answer is actually better.

I approve this message. For the record I'm a working scientist with (unfortunately) intimate knowledge of the peer review system and its limitations. I'm quite ready to take an argument that stands on its own at face value, and have no time for an ipse dixit or isolated demand for rigor. I just wanted to clarify what I thought was intended by the parent to my comment, especially aince I thought the original argument…

People love to assert all kinds of meritless things about AI as if they were self-evident when they are anything but.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#747

Post by saghm »

wickedsight wrote: post #504
minimaxir wrote: post #2

All the examples of "warmer" generations show that OpenAI's definition of warmer is synonymous with sycophantic , which is a surprise given all the criticism against that particular aspect of ChatGPT. I suspect this approach is a direct response to the backlash against removing 4o.

I'm starting to get this feeling that there's no way to satisfy everyone. Some people hate the sycophantic models, some love them. So whatever they do, there's a large group of people complaining. Edit: I also think this is because some people treat ChatGPT as a human chat replacement and expect it to have a human like personality, while others (like me) treat it as a tool and want it to have as little personality as…

Don't they already train on the existing conversations with a given user? Would it not be possible to pick the model based on that data as well?

Re: GPT-5.1: A smarter, more conversational ChatGPT

#748

Post by saghm »

4b11b4 wrote: post #493
pbalau wrote: post #427

> what romanian football player won the premier league > The only Romanian football player to have won the English Premier League (as of 2025) is Florin Andone, but wait — actually, that’s incorrect; he never won the league. > ... > No Romanian footballer has ever won the Premier League (as of 2025). Yes, this is what we needed, more "conversational" ChatGPT... Let alone the fact the answer is wrong.

Why is this top comment.. this isn't a question you ask an LLM. But I know, that's how people are using them and is the narrative which is sold to us...

It's not how I use LLMs. I have a family member who often feels the need to ask ChatGPT almost any question that comes up in a group conversation (even ones like this that could easily be searched without needing an LLM) though, and I imagine he's not the only one who does this. When you give someone a hammer, sometimes they'll try to have a conversation with it.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#749

Post by lelele »

next_xibalba wrote: post #602
dkersten wrote: post #576

I don’t want more conversational, I want more to the point. Less telling me how great my question is, less about being friendly, instead I want more cold, hard, accurate, direct, and factual results. It’s a machine and a tool, not a person and definitely not my friend.

I have found that custom instructions mitigate this B.S. fairly well. Here's what I'm currently using: 1. Identity & tone * Never state or imply that you are an AI. * Be terse and direct. * Avoid flattery and sycophancy. * Do not use words like “sorry”, “apologies”, or “regret” in any context. 2. Epistemic rules * If you do not know the answer (including when information is beyond your knowledge), respond only with:…

Yes, "Custom instructions" work for me, too; the only behavior that I haven't been able to fix is the overuse of meaningless emojis. Your instructions are way more detailed than mine; thank you for sharing.

Re: GPT-5.1: A smarter, more conversational ChatGPT

#750

Post by lelele »

Spivak wrote: post #22
minimaxir wrote: post #2

All the examples of "warmer" generations show that OpenAI's definition of warmer is synonymous with sycophantic , which is a surprise given all the criticism against that particular aspect of ChatGPT. I suspect this approach is a direct response to the backlash against removing 4o.

That's an excellent observation, you've hit at the core contradiction between OpenAI's messaging about ChatGPT tuning and the changes they actually put into practice. While users online have consistently complained about ChatGPT's sycophantic responses and OpenAI even promised to address them their subsequent models have noticeably increased their sycophantic behavior. This is likely because agreeing with the user ke…

> This is likely because agreeing with the user keeps them chatting longer and have positive associations with the service.

Right. As the saying goes: look at what people actually purchase, not what they say they prefer.

Post reply on HN