I wish chatgpt would stop saying things like "here's a no nonsense answer" like maybe just don't include nonsense in the answer?
It's analogous to how politicians nowadays are constantly saying "let me be clear", it drives me nuts.
GPT-5.1: A smarter, more conversational ChatGPT
611–620 of 766 posts
Re: GPT-5.1: A smarter, more conversational ChatGPT
#612> 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.
The best thing is that all this stuff is accounted to your token usage, so they have an adverse incentive :D
This is why people are getting different results with thinking models -- it's as if you were going to be asked ANY question and need to give the correct answer all at once, full stream-of-consciousness.
Yes there are perverse incentives, but I wonder why these sorts of models are available at all tbh.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#613I 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.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#614Earlier quoted context omitted.
Maybe you used "Don't give me nonsense" in your custom system prompt?
That does nothing. You can add, “say I don’t know if you are not certain or don’t know the answer” and it will never say I don’t know.
Anything that you've mentioned in the past (like `no nonsense`) that still exists in context, will have a higher possibility of being generated than other tokens.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#615Re: GPT-5.1: A smarter, more conversational ChatGPT
#616> 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
Re: GPT-5.1: A smarter, more conversational ChatGPT
#617I 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.
...like a google search!
Re: GPT-5.1: A smarter, more conversational ChatGPT
#618I 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.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#619Earlier quoted context omitted.
I really struggle to see a path where $.01 ad inventory covers the cost of inference, much less training or any other of OpenAI ventures. Unless every query makes you watch a 30 second unskippable video or something equally awful.
Users will ask ChatGPT for recommendations and the answer will feature products and services that have paid to be there, probably with some sort of attribution mechanism so OpenAI can get paid extra if the user ends up completing the purchase.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#620Earlier quoted context omitted.
You see people (business people who are enthusiastic about tech, often), claiming that these bots are the new Google and Wikipedia, and that you’re behind the times if you do, what amounts, to looking up information yourself. We’re preaching to the choir by being insistent here that you prompt these things to get a “vibe” about a topic rather than accurate information, but it bears repeating.
Out of curiosity, is this a question you think Google is well-suited to answer^? How many Wikipedia pages will you need to open to determine the answer? When folks are frustrated because they see a bizarre question that is an extreme outlier being touted as "model still can't do _" part of it is because you've set the goalposts so far beyond what traditional Google search or Wikipedia are useful for. ^ I spent about…