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

521–530 of 766 posts

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

#521

Post by skywhopper »

kenjackson wrote: post #509
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…

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).

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

#522

Post by kachapopopow »

I think what a lot of people are missing here is that openai understands that long-term their primary user-base will be people just wanting to talk to someone about something rather than being focused on programming or problem solving as dystopian as it sounds. Seeing as they are transitioning towards a for-profit business it makes sense for them to target what people call 'normies' since that is at least 70%-90% of the world.

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

#523

Post by Veen »

kachapopopow wrote: post #522

I think what a lot of people are missing here is that openai understands that long-term their primary user-base will be people just wanting to talk to someone about something rather than being focused on programming or problem solving as dystopian as it sounds. Seeing as they are transitioning towards a for-profit business it makes sense for them to target what people call 'normies' since that is at least 70%-90% of…

That and people who want to use it to make porn.

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

#524

Post by skywhopper »

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.

The main change in 5 (and the reason for disabling other models) was to allow themselves to dynamically switch modes and models on the backend to minimize cost. Looks like this is a further tweak to revive the obsequious tone (which turned out to be crucial to the addicted portion of their user base) while still doing the dynamic processing.

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

#526

Post by engeljohnb »

adriand wrote: post #474
elif wrote: post #469

Earlier quoted context omitted.

Another one I like to use is "never apologize or explain yourself. You are not a person you are an algorithm. No one wants to understand the reasons why your algorithm sucks. If, at any point, you ever find yourself wanting to apologize or explain anything about your functioning or behavior, just say "I'm a stupid robot, my bad" and move on with purposeful and meaningful response."

I think this is unethical. Humans have consistently underestimated the subjective experience of other beings. You may have good reasons for believing these systems are currently incapable of anything approaching consciousness, but how will you know if or when the threshold has been crossed? Are you confident you will have ceased using an abusive tone by then? I don’t know if flies can experience pain. However, I’m no…

I think current LLM chatbots are too predictable to be conscious.

But I still see why some people might think this way.

"When a computer can reliably beat humans in chess, we'll know for sure it can think."

"Well, this computer can beat humans in chess, and it can't think because it's just a computer."

...

"When a computer can create art, then we'll know for sure it can think."

"Well, this computer can create art, and it can't think because it's just a computer."

...

"When a computer can pass the Turing Test, we'll know for sure it can think."

And here we are.

Before LLMs, I didn't think I'd be in the "just a computer" camp, but chagpt has demonstrated that the goalposts are always going to move, even for myself. I'm not smart enough to come up with a better threshold to test intelligence than Alan Turing, but chatgpt passes it and chatgpt definitely doesn't think.

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

#527

Post by ndriscoll »

adriand wrote: post #497
pebble wrote: post #484

Earlier quoted context omitted.

Do you apologize to table corners when you bump into them?

Likening machine intelligence to inert hunks of matter is not a very persuasive counterargument.

What if it's the same hunk of matter? If you run a language model locally, do you apologize to it for using a portion of its brain to draw your screen?

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

#528

Post by igravious »

embedding-shape wrote: post #511
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…

I agree a lot with the first part, the only time I actually feel productive with them is when I can have a short feedback cycle with 100% proof if it's correct or not, as soon as "manual human verification" is needed, things spiral out of control quickly. > Sure, the machine can give you its sources but it won't tell you about sources it ignored. You can prompt for that though, include something like "Include all the…

> You can prompt for that though, include something like "Include all the sources you came across, and explain why you think it was irrelevant" and unsurprisingly, it'll include those. I've also added a "verify_claim" tool which it is instructed to use for any claims before sharing a final response, checks things inside a brand new context, one call per claim. So far it works great for me with GPT-OSS-120b as a local agent, with access to search tools.

Feel like this should be built in?

Explain your setup in more detail please?

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

#529

Post by chud37 »

Quarrel wrote: post #440
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.

My worry is that they're training it on Q&A from the general public now, and that this tone, and more specifically, how obsequious it can be, is exactly what the general public want. Most of the time, I suspect, people are using it like wikipedia, but with a shortcut to cut through to the real question they want answered; and unfortunately they don't know if it is right or wrong, they just want to be told how bright…

Its very frustating that it can't be relied upon. I was asking gemini this morning about Uncharted 1,2 and 3 if they had a remastered version for the PS5. It said no. Then 5 minutes later I on the PSN store there were the three remastered versions for sale.

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

#530

Post by r_lee »

0xdeafbeef wrote: post #472
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.

https://chatgpt.com/s/t_6915c8bd1c80819183a54cd144b55eb2 Damn this is a lot of self correcting

Lmao what the hell have they made
Post reply on HN