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

711–720 of 766 posts

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

#711

Post by mrguyorama »

thewebguyd wrote: post #181
qsort wrote: post #167

Earlier quoted context omitted.

> 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…

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 day.

The ship computer on the Enterprise did not make conversation. When Dr Crusher asked it the size of the universe, it did not say "A few hundred meters, wow that's pretty odd why is the universe so small?" it responded "A few hundred meters".

The computer was not a character.

Picard did not ask the computer it's opinion on the political situation he needed to solve that day. He asked it to query some info, and then asked his room full of domain experts their opinions.

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

#712

Post by trogdor »

oceliker wrote: post #704
trogdor wrote: post #668

Earlier quoted context omitted.

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.

Did you start a new chat? It doesn't apply to existing chats (probably because it works through the system prompt). I have been using the Robot (Efficient) setting for a while and never had a response like that.

Followup: there is a very noticeable change in my written conversations with ChatGPT. It seems that there is no change in voice mode.

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

#713

Post by everdev »

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.

We live in a culture that wants to humanize robots and dehumanize people.

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

#715

Post by jug »

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.

Use the "Efficient" persona in the ChatGPT settings. Formerly known as "Robot".

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

#716

Post by xmcqdpt2 »

btown wrote: post #577
xmcqdpt2 wrote: post #499

Earlier quoted context omitted.

LLMs only really make sense for tasks where verifying the solution (which you have to do!) is significantly easier than solving the problem: translation where you know the target and source languages, agentic coding with automated tests, some forms of drafting or copy editing, etc. General search is not one of those! Sure, the machine can give you its sources but it won't tell you about sources it ignored. And verify…

One of the dangers of automated tests is that if you use an LLM to generate tests, it can easily start testing implemented rather than desired behavior. Tell it to loop until tests pass, and it will do exactly that if unsupervised. And you can’t even treat implementation as a black box, even using different LLMs, when all the frontier models are trained to have similar biases towards confidence and obsequiousness in…

Not only can it easily do this, I've found that Claude models do this as a matter of course. My strategy now has been to either write the test or write the implementation and use Claude for the other one. That keeps it a lot more honest.

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

#717

Post by xmcqdpt2 »

skywhopper wrote: post #521
kenjackson wrote: post #509

Earlier quoted context omitted.

Don’t search engines have the same problem? You don’t get back a list of sites that the engine didn’t prefer for some reason.

With search engine results you can easily see and judge the quality of the sources. With LLMs, even if they link to sources, you can’t be sure they are accurately representing the content. And once your own mind has been primed with the incorrect summary, it’s harder to pull reality out of the sources, even if they’re good (or even relevant — I find LLMs often pick bad/invalid sources to build the summary result).

Exactly. I've gotten much more interested by LLM now that i've accepted I can just look at the final result (code) without having to read any of the justification wall of text, which is generally convincing bullshit.

It's like working with a very cheap, extremely fast, dishonest and lazy employee. You can still get them to help you but you have to check them all the time.

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

#718

Post by antegamisou »

bongodongobob wrote: post #691
hellohihello135 wrote: post #584

The amount of grumpiness in this comment thread is amazing.

I know I'm personally just tired of trying to converse with people with heads in the sand. AI saves me shit tons of time daily. If they can't figure it out, so be it. The level of absolute denial in HN AI threads is bizarre. One guess is that hacker nerds have their entire personality tied to being a smart haxor. That is being commoditized and they are getting defensive about it. It's telling that the image/video AI…

Not everyone writes trivial frontend or sysadmins for a living.

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

#719

Post by make3 »

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.

That's one of the things that users think they want, but use the product 30x when it's not actually that way, a bit like follow-only mode by default on Twitter etc.

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

#720

Post by rtaylorgarlock »

jwr wrote: post #681

This is why I prefer models from Anthropic, especially for language-related tasks: they are more natural and to the point. GPT always used too much corporate-speak and market-speak, and this recent update looks terrible: I do not want my AI assistant to crack jokes, be sycophantic, or say "I’ve got you, Ron". I want it to assist me without pretending to be something that it isn't.

In my experience, somehow the strength in natural language / litigious / prosaic work translated negatively in a way to coding. The verbose, prolific way it writes + the investment into dev tooling by Anthropic resulted in Anthropic's models leading the sycophantic-presumptuous-over-confident frontier. So much so that I still have barely used Sonnet 4.5 thinking.
Post reply on HN