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

541–550 of 766 posts

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

#541

Post by KronisLV »

airstrike wrote: post #261
KronisLV wrote: post #223

Earlier quoted context omitted.

> I mean, yes, but also because it's not as good as Claude today. I'm not sure, sometimes GPT-5 Codex (or even the regular GPT-5 with Medium/High reasoning) can do things Sonnet 4.5 would mess up (most recently, figuring out why some wrappers around PrimeVue DataTable components wouldn't let the paginator show up and work correctly; alongside other such debugging) and vice versa, sometimes Gemini 2.5 Pro is also pret…

Out of curiosity, did you try asking Opus 4.1 as well?

Afraid not, a bit outside of my budget (given that I've been pushing millions of tokens daily, especially for lots of refactoring that'd be great to do in an automated fashion but codegen solutions for which... just don't exist). From what little I've used Opus in the past, I'm sure it'd do reasonably as well. Maybe even Sonnet with more attempts, different prompts etc.

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

#542

Post by embedding-shape »

igravious wrote: post #528
embedding-shape wrote: post #511

Earlier quoted context omitted.

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…

> Feel like this should be built in?

Not everyone uses LLMs the same way, which is made extra clear because of the announcement this submission is about. I don't want conversational LLMs, but seems that perspective isn't shared by absolutely everyone, and that makes sense, it's a subjective thing how you like to be talked/written to.

> Explain your setup in more detail please?

I don't know what else to tell you that I haven't said already :P Not trying to be obtuse, just don't know what sort of details you're looking for. I guess in more specific terms; I'm using llama.cpp(/llama-server) as the "runner", and then I have a Rust program that acts as the CLI for my "queries", and it makes HTTP requests to llama-server. The requests to llama-server includes "tools", where one of those is a "web_search" tool hooked up to a local YaCy instance, another is "verify_claim" which basically restarts a new separate conversation inside the same process, with access to a subset of the tools. Is that helpful at all?

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

#543

Post by dns_snek »

amosjyng wrote: post #246
jsrozner wrote: post #235

Earlier quoted context omitted.

One difference is that if it were found that a psychiatrist or other professional had encouraged a patient's delusions or suicidal tendencies, then that person would likely lose his/her license and potentially face criminal penalties. We know that humans should be able to consider the consequences of their actions and thus we hold them accountable (generally). I'd be surprised if comparisons in the self-driving space…

> that person would likely lose his/her license and potentially face criminal penalties. What if it were an unlicensed human encouraging someone else's delusions? I would think that's the real basis of comparison, because these LLMs are clearly not licensed therapists, and we can see from the real world how entire flat earth communities have formed from reinforcing each others' delusions. Automation makes things easi…

> I would think that's the real basis of comparison

It's not because that's not the typical case. LLMs encourage people's delusions by default, it's just a question of how receptive you are to them. Anyone who's used ChatGPT has experienced it even if they didn't realize it. It starts with "that's a really thoughtful question that not many people think to ask", and "you're absolutely right [...]".

> If AI is better at meeting human needs than actual humans are, why let perfect be the enemy of good?

There is no good that comes from having all of your perspective distortions validated as facts. They turn into outright delusions without external grounding.

Talk to ChatGPT and try to put yourself into the shoes of a hurtful person (e.g. what people would call "narcissistic") who's complaining about other people. Keep in mind that they almost always suffer from a distorted perception so they genuinely believe that they're great people.

They can misunderstand some innocent action as a personal slight, react aggressively, and ChatGPT would tell them they were absolutely right to get angry. They could do the most abusive things and as long as they genuinely believe that they're good people (as they almost always do), ChatGPT will reassure them that other people are the problem, not them.

It's hallucinations feeding into hallucinations.

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

#544

Post by gizajob »

torben-friis wrote: post #455
Quarrel wrote: post #440

Earlier quoted context omitted.

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…

I’m of two minds about this. The ass licking is dangerous to our already too tight information bubbles, that part is clear. But that aside, I think I prefer a conversational/buddylike interaction to an encyclopedic tone. Intuitively I think it is easier to make the connection that this random buddy might be wrong, rather than thinking the encyclopedia is wrong. Casualness might serve to reduce the tendency to think o…

Sam Altman probably can’t handle any GPT models that don’t ass lick to an extreme degree so they likely get nerfed before they reach the public.

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

#545

Post by nl »

saaaaaam wrote: post #222
thewebguyd wrote: post #177

Earlier quoted context omitted.

> So I think normies maybe do want a more conversational ChatGPT. The backlash from GPT-5 proved that. The normies want a very different LLM from what you or I might want, and unfortunately OpenAI seems to be moving in a more direct-to-consumer focus and catering to that. But I'm really concerned. People don't understand this technology, at all. The way they talk to it, the suicide stories, etc. point to people in ge…

I just cannot imagine myself sitting just “chatting away” with an AI. It makes me feel quite sick to even contemplate it. Another person I was talking to recently kept referring to ChatGPT as “she”. “She told me X”, “and I said to her…” Very very odd, and very worrying. As you say, a big education problem. The interesting thing is that a lot of these people are folk who are on the edges of digital literacy - people w…

Why is it odd?

Some people treat their pets like they humans. Not sure why this is worse particularly.

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

#547

Post by NuclearPM »

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.

Just ask for sources. Problem solved.

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

#548

Post by javcasas »

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.

Oh yeah, yes, baby, burn those tokens, yes! The more you burn the bigger the invoice!

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

#549

Post by hamburgererror »

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.

Meanwhile on duck.ai

ChatGPT 4o-mini, 5 mini and OSS 120B gave me wrong answers.

Llama 4 Scout completely broke down.

Claude Haiku 3.5 and Mistral Small 3 gave the correct answer.

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

#550

Post by nkrisc »

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…

> 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 work off of ("one-shot").

That is the usage that is advertised to the general public, so I think it's fair to critique it by way of this usage.

Post reply on HN