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

181–190 of 766 posts

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

#181

Post by thewebguyd »

qsort wrote: post #167
engeljohnb wrote: post #107

Seems like people here are pretty negative towards a "conversational" AI chatbot. Chatgpt has a lot of frustrations and ethical concerns, and I hate the sycophancy as much as everyone else, but I don't consider being conversational to be a bad thing. It's just preference I guess. I understand how someone who mostly uses it as a google replacement or programming tool would prefer something terse and efficient. I fall…

> I've dreamed about a computer assistant that can respond to natural language When we dreamed about this as kids, we were dreaming about Data from Star Trek, not some chatbot that's been focus grouped and optimized for engagement within an inch of its life. LLMs are useful for many things and I'm a user myself, even staying within OpenAI's offerings, Codex is excellent, but as things stand anthropomorphizing models…

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 tea?"

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

#182

Post by pants2 »

tekacs wrote: post #60
url00 wrote: post #11

I don't want a more conversational GPT. I want the _exact_ opposite. I want a tool with the upper limit of "conversation" being something like LCARS from Star Trek. This is quite disappointing as a current ChatGPT subscriber.

That's what the personality selector is for: you can just pick 'Efficient' (formerly Robot) and it does a good job of answering tersely? https://share.cleanshot.com/9kBDGs7Q

FWIW I didn't like the Robot / Efficient mode because it would give very short answers without much explanation or background. "Nerdy" seems to be the best, except with GPT-5 instant it's extremely cringy like "I'm putting my nerd hat on - since you're a software engineer I'll make sure to give you the geeky details about making rice."

"Low" thinking is typically the sweet spot for me - way smarter than instant with barely a delay.

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

#183

Post by pgsandstrom »

nathan_compton wrote: post #24
url00 wrote: post #11

I don't want a more conversational GPT. I want the _exact_ opposite. I want a tool with the upper limit of "conversation" being something like LCARS from Star Trek. This is quite disappointing as a current ChatGPT subscriber.

You can just tell the AI to not be warm and it will remember. My ChatGPT used the phrase "turn it up to eleven" and I told it never to speak in that manner ever again and its been very robotic ever since.

I added the custom instruction "Please go straight to the point, be less chatty". Now it begins every answer with: "Straight to the point, no fluff:" or something similar. It seems to be perfectly unable to simply write out the answer without some form of small talk first.

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

#184

Post by tedsanders »

ipsum2 wrote: post #95

I've been using GPT-5.1-thinking for the last week or so, it's been horrendous. It does not spend as much time thinking as GPT-5 does, and the results are significantly worse (e.g. obvious mistakes) and less technical. I suspect this is to save on inference compute. I've temporarily switched back to o3, thankfully that model is still in the switcher. edit: s/month/week

Not possible. GPT-5.1 didn’t exist a month ago. I helped train it.

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

#185

Post by logicprog »

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.

This is why I like Kimi K2/Thinking. IME it pushes back really, really hard on any kind of non obvious belief or statement, and it doesn't give up after a few turns — it just keeps going, iterating and refining and restating its points if you change your mind or taken on its criticisms. It's great for having a dialectic around something you've written, although somewhat unsatisfying because it'll never agree with you, but that's fine, because it isn't a person, even if my social monkey brain feels like it is and wants it to agree with me sometimes. Someone even ran a quick and dirty analysis of which models are better or worse at pushing back on the user and Kimi came out on top:

https://www.lesswrong.com/posts/iGF7YcnQkEbwvYLPA/ai-induced...

See also the sycophancy score of Kimi K2 on Spiral-Bench: https://eqbench.com/spiral-bench.html (expand details, sort by inverse sycophancy).

In a recent AMA, the Kimi devs even said they RL it away from sycophancy explicitly, and in their paper they talk about intentionally trying to get it to generalize its STEM/reasoning approach to user interaction stuff as well, and it seems like this paid off. This is the least sycophantic model I've ever used.

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

#186

Post by thedrexster »

The_Rob wrote: post #136
DonaldPShimoda wrote: post #125

Earlier quoted context omitted.

This is like arguing that we shouldn't try to regulate drugs because some people might "want" the heroin that ruins their lives. The existing "personalities" of LLMs are dangerous, full stop. They are trained to generate text with an air of authority and to tend to agree with anything you tell them. It is irresponsible to allow this to continue while not at least deliberately improving education around their use. Thi…

Comparing LLM responses to heroine is insane.

heroin is the drug, heroine is the damsel :)

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

#187

Post by Chance-Device »

A lot of negativity towards this and OpenAI in general. While skepticism is always good I wonder if this has crossed the line from reasoned into socially reinforced dogpiling.

My own experience with GPT 5 thinking and its predecessor o3, both of which I used a lot, is that they were super difficult to work with on technical tasks outside of software. They often wrote extremely dense, jargon filled responses that often contained fairly serious mistakes. As always the problem was/is that the mistakes were peppered in with some pretty good assistance and knowledge and its difficult to tell what’s what until you actually try implementing or simulating what is being discussed, and find it doesn’t work, sometimes for fundamental reasons that you would think the model would have told you about. And of course once you pointed these flaws out to the model, it would then explain the issues to you as if it had just discovered these things itself and was educating you about them. Infuriating.

One major problem I see is the RLHF seems to have shaped the responses so they only give the appearance of being correct to a reasonable reader. They use a lot of social signalling that we associate with competence and knowledgeability, and usually the replies are quite self consistent. That is they pass the test of looking to a regular person like a correct response. They just happen not to be. The model has become expert at fooling humans into believing what it’s saying rather than saying things that are functionally correct, because the RLHF didn’t rely on testing anything those replies suggested, it only evaluated what they looked like.

However, even with these negative experiences, these models are amazing. They enable things that you would simply not be able to get done otherwise, they just come with their own set of problems. And humans being humans, we overlook the good and go straight to the bad. I welcome any improvements to these models made today and I hope OpenAI are able to improve these shortcomings in the future.

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

#188

Post by blueboo »

joering2 wrote: post #59
schmeichel wrote: post #4

Gemini 2.5 Pro is still my go to LLM of choice. Haven't used any OpenAI product since it released, and I don't see any reason why I should now.

No matter how I tried, Google AI did not want to help me write appeal brief response to ex-wife lunatic 7-point argument that 3 appellant lawyers quoted between $18,000 and $35,000. The last 3 decades of Google's scars and bruises of never-ending lawsuits and consequences of paying out billions in fines and fees, felt like reasonable hesitation on Google part, comparing to new-kid-on-the-block ChatGPT who did not hes…

What? AI assistants are prohibited from providing legal and/or medical advice. They're not lawyers (nor doctors).

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

#189

Post by Y_Y »

sbuttgereit wrote: post #75
url00 wrote: post #11

I don't want a more conversational GPT. I want the _exact_ opposite. I want a tool with the upper limit of "conversation" being something like LCARS from Star Trek. This is quite disappointing as a current ChatGPT subscriber.

This. When I go to an LLM, I'm not looking for a friend, I'm looking for a tool. Keeping faux relationships out of the interaction never let's me slip into the mistaken attitude that I'm dealing with a colleague rather than a machine.

I don't know about you, but half my friends are tools.
Post reply on HN