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

291–300 of 766 posts

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

#291

Post by qwertytyyuu »

Bolwin wrote: post #193
bonesss wrote: post #151

Earlier quoted context omitted.

Speech to text makes it feel more futuristic. As does reflecting that Picard had to explain to Computer every, single, time that he wanted his Earl Grey tea ‘hot’. We knew what was coming.

I don't speak any faster than I type, despite what the transcription companies claim

Most people don't at 150wpm, the typically speaking speed, even agmonst technical people. For regular questions without that don't invovle precise syntax like in maths and programming, speech would be faster. Though reading the output would be faster than hearing it spoken

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

#292

Post by brookst »

DonaldPShimoda wrote: post #216
simonw wrote: post #138

Earlier quoted context omitted.

What's your proposed solution here? Are you calling for legislation that controls the personality of LLMs made available to the public?

At the very least, I think there is a need for oversight of how companies building LLMs market and train their models. It's not enough to cross our fingers that they'll add "safeguards" to try to detect certain phrases/topics and hope that that's enough to prevent misuse/danger — there's not sufficient financial incentive for them to do that of their own accord beyond the absolute bare minimum to give the appearance…

I work on one of these products. An incredible amount of money and energy goes into safety. Just a staggering amount. Turns out it’s really hard.

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

#293

Post by qwertytyyuu »

emp17344 wrote: post #150
Szpadel wrote: post #12

isn't that weird there are no benchmarks included on this release?

Probably because it’s not that much better than GPT-5 and they want to keep the AI train moving.

even if its slightly better, they might still have released the benchmarks and called it a incremental improvement. I think that its falls behind one some compared to chat gpt5

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

#294

Post by danmaz74 »

joquarky wrote: post #250
pgsandstrom wrote: post #183

Earlier quoted context omitted.

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.

Aren't these still essentially completion models under the hood? If so, my understanding for these preambles is that they need a seed to complete their answer.

But the seed is the user input.

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

#295

Post by jstummbillig »

wewtyflakes wrote: post #290
abound wrote: post #268

Earlier quoted context omitted.

In defense of OpenAI in this particular situation, GPT 5 can be incredibly jargon-y at times, making it much worse of a learning tool than other LLMs. Here's some response snippets from me asking a question about dual-stack networking: > Get an IPv6 allocation from your RIR and IPv6 transit/peering. Run IPv6 BGP with upstreams and in your core (OSPFv3/IS-IS + iBGP). > Enable IPv6 on your access/BNG/BRAS/CMTS and aggr…

Asking it to clarify costs nothing and you end up getting up to speed with the language of the domain; everyone wins.

> Asking it to clarify costs nothing

It costs the most important thing I got

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

#296

Post by wowkise »

Sadly, OpenAI models have overzealous filters regarding Cybersecurity. it refuses to engage on any thing related to it compared to other models like anthropic claude and grok. Beyond basic uses, it's useless in that regard and no amount of prompt engineering seems to force it to drop this ridiculous filter.

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

#298

Post by Auracle »

pgsandstrom wrote: post #183
nathan_compton wrote: post #24

Earlier quoted context omitted.

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.

I had a similar instruction and in voice mode I had it trying to make a story for a game that my daughter and I were playing where it would occasionally say “3,2,1 go!” or perhaps throw us off and say “3,2,1, snow!” or other rhymes.

Long story short it took me a while to figure out why I had to keep telling it to keep going and the story was so straightforward.

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

#299

Post by mabedan »

mips_avatar wrote: post #269

I wish chatgpt would stop saying things like "here's a no nonsense answer" like maybe just don't include nonsense in the answer?

Right? That drives me crazy. It only does that for me in the voice mode. And in cases I ask it to elaborate, it ignores my request and repeats the system instructions from my preferences “ok, I’ll keep it concise” and gives a 5 word answer

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

#300

Post by mips_avatar »

mabedan wrote: post #299
mips_avatar wrote: post #269

I wish chatgpt would stop saying things like "here's a no nonsense answer" like maybe just don't include nonsense in the answer?

Right? That drives me crazy. It only does that for me in the voice mode. And in cases I ask it to elaborate, it ignores my request and repeats the system instructions from my preferences “ok, I’ll keep it concise” and gives a 5 word answer

It's some kind of shortcut these models are getting in alignment because the base models don't do that stuff
Post reply on HN