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

591–600 of 766 posts

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

#591

Post by AJ007 »

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…

"one call per claim" I wonder how long it takes for it to be common knowledge how important this is. Starting to think never. Great idea by the way, I should try this.

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

#592

Post by hypercube33 »

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.

One of my saved memories is to always give shorter "chat like" concise to the point answers and give further description if prompted to only

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

#593

Post by ahsillyme »

captainkrtek wrote: post #15
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.

Id have more appreciation and trust in an llm that disagreed with me more and challenged my opinions or prior beliefs. The sycophancy drives me towards not trusting anything it says.

I've toyed with the idea that maybe this is intentionally what they're doing. Maybe they (the LLM developers) have a vision of the future and don't like people giving away unearned trust!

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

#594

Post by danlugo92 »

brookst wrote: post #585
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.

You’re in the minority here. I get it. I prefer cars with no power steering and few comforts. I write lots of my own small home utility apps. That’s just not the relationship most people want to have with tech and products.

A better analogy might be those automated braking systems, that also tend to brake your car randomly btw.

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

#595

Post by embedding-shape »

AJ007 wrote: post #591
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…

"one call per claim" I wonder how long it takes for it to be common knowledge how important this is. Starting to think never. Great idea by the way, I should try this.

I've been trying to figure out ways of highlighting why it's important and how it actually works, maybe some heatmap of the attention of previous tokens, so people can see visually how messed up things become once even two concepts at the same time are mixed.

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

#596

Post by elil17 »

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.

I'm guessing that is the most common view for many users, but their paying users are the people who are more likely to have some kind of delusional relationship/friendship with the AI.

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

#597

Post by ta12653421 »

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.

Just put your requirements as the first sentence in your prompts and it will work.

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

#598

Post by ta12653421 »

ta12653421 wrote: post #597
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.

Just put your requirements as the first sentence in your prompts and it will work.

add on: You can even prime it that it should shout at you and treat you like an ass*** if you prefer that :-)
Post reply on HN