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

551–560 of 766 posts

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

#551

Post by theoldgreybeard »

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.

I really only use LLMs for coding and IT related questions. I've had Claude self-correct itself several times about how something might be the more idiomatic way do do something after starting to give me the answer. For example, I'll ask how to set something up in a startup script and I've had it start by giving me strict POSIX syntax then self-correct once it "realizes" that I am using zsh.

I find it amusing, but also I wonder what causes the LLM to behave this way.

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

#552

Post by hamburgererror »

4b11b4 wrote: post #533
hamburgererror wrote: post #500

Earlier quoted context omitted.

What do you ask them then?

I'll respond to this bait in the hopes that it clicks for someone how to _not_ use an LLM.. Asking "them"... your perspective is already warped. It's not your fault, all the text we've previously ever seen is associated with a human being. Language models are mathematical, statistical beasts. The beast generally doesn't do well with open ended questions (known as "zero-shot"). It shines when you give it something to…

I was not trolling actually, thanks for your detailed answer. I don't use LLMs so much so I didn't know they work better the way you describe.

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

#553

Post by umvi »

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.

"This is an excellent observation, and gets at the heart of the matter!"

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

#554

Post by skywhopper »

Libidinalecon wrote: post #257
varenc wrote: post #3

Interesting that they're releasing separate gpt-5.1-instant and gpt-5.1-thinking models. The previous gpt-5 release made of point of simplifying things by letting the model choose if it was going to use thinking tokens or not. Seems like they reversed course on that?

I was prepared to be totally underwhelmed but after just a few questions I can tell that 5.1 Thinking is all I am going to ever use. Maybe it is just the newness but I quite like how it responded to my standard list of prompts that I pretty much always start with on a new model. I really was ready to take a break from my subscription but that is probably not happening now. I did just learn some nice new stuff with my…

Curious what you learned?

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

#555

Post by downsplat »

estebarb wrote: post #457
crazygringo wrote: post #218

Earlier quoted context omitted.

Sure: Please maintain a strictly objective and analytical tone. Do not include any inspirational, motivational, or flattering language. Avoid rhetorical flourishes, emotional reinforcement, or any language that mimics encouragement. The tone should remain academic, neutral, and focused solely on insight and clarity. Works like a charm for me. Only thing I can't get it to change is the last paragraph where it always t…

I have been somewhat able to remove them with: Do not offer me calls to action, I hate them.

Calls to action seem to be specific to chatgpt's online chat interface. I use it mostly through a "bring your API key" client, and get none of that.

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

#556

Post by 827a »

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.

> You’re rattled, so your brain is doing that thing where it catastrophizes a tiny mishap into a character flaw. But honestly? People barely register this stuff.

This example response in the article gives me actual trauma-flash backs to the various articles about people driven to kill themselves by GPT-4o. Its the exact same sentence structure.

GPT-5.1 is going to kill more people.

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

#557

Post by transcriptase »

captainkrtek wrote: post #15
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.

Id have more appreciation and trust in an llm that disagreed with me more and challenged my opinions or prior beliefs. The sycophancy drives me towards not trusting anything it says.

Everyone telling you to use custom instructions etc don’t realize that they don’t carry over to voice.

Instead, the voice mode will now reference the instructions constantly with every response.

Before:

Absolutely, you’re so right and a lot of people would agree! Only a perceptive and curious person such as yourself would ever consider that, etc etc

After:

Ok here’s the answer! No fluff, no agreeing for the sake of agreeing. Right to the point and concise like you want it. Etc etc

And no, I don’t have memories enabled.

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

#558

Post by skywhopper »

abound wrote: post #268
Dilettante_ wrote: post #170

>GPT‑5.1 Thinking’s responses are also clearer, with less jargon and fewer undefined terms Oh yeah that's what I want when asking a technical question! Please talk down to me, call a spade an earth-pokey-stick and don't ever use a phrase or concept I don't know because when I come face-to-face with something I don't know yet I feel deep insecurity and dread instead of seeing an opportunity to learn! But I assume thei…

In defense of OpenAI in this particular situation, GPT 5 can be incredibly jargon-y at times, making it much worse of a learning tool than other LLMs. Here's some response snippets from me asking a question about dual-stack networking: > Get an IPv6 allocation from your RIR and IPv6 transit/peering. Run IPv6 BGP with upstreams and in your core (OSPFv3/IS-IS + iBGP). > Enable IPv6 on your access/BNG/BRAS/CMTS and aggr…

I always wonder how useful such explanations could be. If you don’t know (or can’t guess) what ICMPv6 is (and how much would knowing it stands for “Internet Control Message Protocol version 6” help?), perhaps you asked the wrong question or, yes, you’re dangerously out of your depth and shouldn’t be trying to implement a networking stack without doing some more research.

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

#559

Post by skywhopper »

jstummbillig wrote: post #295
wewtyflakes wrote: post #290

Earlier quoted context omitted.

Asking it to clarify costs nothing and you end up getting up to speed with the language of the domain; everyone wins.

> Asking it to clarify costs nothing It costs the most important thing I got

Why are you even doing this if you don’t want to learn? And if you can’t be bothered to ask questions, are you even serious about learning?
Post reply on HN