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

661–670 of 766 posts

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

#661

Post by BeetleB »

engeljohnb wrote: post #641
BeetleB wrote: post #635

Earlier quoted context omitted.

> 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. But is this realistic conversation? If I say to a human I don't know "I'm feeling stressed and could use some relaxation tips" and he responds with "I’ve got you, Ron" I'd want to reduce my interactions with him. If I ask someone to explain a techni…

Yes, it's true that I have different expectations from a conversation with a computer program than with a real human. Like I said, I don't think of it the same as a friend.

I'm with you in that I like conversational AI. I just wish it wasn't obvious it's an AI and actually sounded like real humans. :-)

The format matters as well. Some of these things may sound just fine in audio, but it doesn't translate well to text.

Also, context matters. Sometimes I just want to have a conversation. Other times I'm trying to solve a problem. For the latter, the extra fluff is noise and my brain has to work harder to solve the problem than I feel it should.

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

#662

Post by transcriptase »

mattcantstop wrote: post #659

One of the main things that I want changed for conversation mode is I don't want it to be so sensitive to any background noise. ChatGPT can be reciting back and answer and someone across the room turns a page in a book and it stops dictating, and then, instead of finishing the previous answer, starts to answer the same question in a different way. ChatGPT is way too deferential for any noise during the conversation.

Including itself sometimes in an otherwise silent environment.

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

#663

Post by NewUser76312 »

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.

OK but surely it can do this given your instructional prompting. I get they have a default behavior, which perhaps isn't your (or my) preference.

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

#664

Post by trashface »

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.

It has this, "Robot" personality in settings and has been there for a few months at least.

Edited - it appears to have been renamed "Efficient".

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

#665

Post by aaroninsf »

OpenAI openly moving engagement farming is the tip of the iceberg.

The bottom of the iceberg is how this is going to work out in the context of surveillance capitalism.

If ChatGPT is losing money, what's the plan to get off the runway...?

What is the benefit in establishing monopoly or dominance in the space, if you lose money when customers use your product...?

OpenAI's current published privacy policies preclude sale of chat history or disclosure to partners for such purposes (AFAIK).

I'm going to keep an eye on that.

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

#666

Post by mezi »

standardly wrote: post #645

GPT-5.1 IS a smarter, more conversational ChatGPT, and I love that you mentioned it - you're really getting down to the heart - to the very essence - of how conversational ChatGPT can be. Would you like me to write a short, to-the-point HN post to really emphasize how conversational GPT-5.1 can be?

The horror of the triple emdash

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

#668

Post by trogdor »

mhink wrote: post #660
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.

TFA mentions that they added personality presets earlier this year, and just added a few more in this update: > Earlier this year, we added preset options to tailor the tone of how ChatGPT responds. Today, we’re refining those options to better reflect the most common ways people use ChatGPT. Default, Friendly (formerly Listener), and Efficient (formerly Robot) remain (with updates), and we’re adding Professional, Ca…

I just changed my ChatGPT personality setting to “Efficient.” It still starts every response with “Yeah, definitely! Let’s talk about that!” — or something similarly inefficient.

So annoying.

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

#670

Post by aeve890 »

dickiedyce wrote: post #615

Warmer = US centric? I always think that the proliferation of J.A.R.V.I.S.-type projects in the wild is down to the writing in Iron Man, and Paul Bettany's dry delivery. We want dryer, not warmer. More sarcasm, less smarm.

>More sarcasm

Please don't. The internet is already full of clowns trying to be the most sarcastic one in the thread.

Post reply on HN