Holy em-dash fest in the examples, would have thought they'd augment the training dataset to reduce this behavior.
Right? This was my first thought too.
GPT-5.1: A smarter, more conversational ChatGPT
211–220 of 766 posts
Re: GPT-5.1: A smarter, more conversational ChatGPT
#212Earlier quoted context omitted.
Sorry that you can't control other peoples lives & wants
This is like arguing that we shouldn't try to regulate drugs because some people might "want" the heroin that ruins their lives. The existing "personalities" of LLMs are dangerous, full stop. They are trained to generate text with an air of authority and to tend to agree with anything you tell them. It is irresponsible to allow this to continue while not at least deliberately improving education around their use. Thi…
Who are you to determine what other people want? Who made you god?
Re: GPT-5.1: A smarter, more conversational ChatGPT
#213Earlier quoted context omitted.
Which model are you talking about here?
The one that I said in my comment, GPT-5 Thinking Mini.
I was confused when you said "Before GPT-5 was released it used to be a perfect compromise between a "dumb" non-Thinking model and a SLOW Thinking model" - so I guess you mean the difference between GPT-4o and o3 there?
Re: GPT-5.1: A smarter, more conversational ChatGPT
#214Earlier quoted context omitted.
This is like arguing that we shouldn't try to regulate drugs because some people might "want" the heroin that ruins their lives. The existing "personalities" of LLMs are dangerous, full stop. They are trained to generate text with an air of authority and to tend to agree with anything you tell them. It is irresponsible to allow this to continue while not at least deliberately improving education around their use. Thi…
Comparing LLM responses to heroine is insane.
I'm not saying they're equivalent; I'm saying that they're both dangerous, and I think taking the position that we shouldn't take any steps to prevent the danger because some people may end up thinking they "want" it is unreasonable.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#215Earlier quoted context omitted.
This is like arguing that we shouldn't try to regulate drugs because some people might "want" the heroin that ruins their lives. The existing "personalities" of LLMs are dangerous, full stop. They are trained to generate text with an air of authority and to tend to agree with anything you tell them. It is irresponsible to allow this to continue while not at least deliberately improving education around their use. Thi…
Who are you to determine what other people want? Who made you god?
...nobody? I didn't determine any such thing. What I was saying was that LLMs are dangerous and we should treat them as such, even if that means not giving them some functionality that some people "want". This has nothing to do with playing god and everything to do with building a positive society where we look out for people who may be unable or unwilling to do so themselves.
And, to be clear, I'm not saying we necessarily need to outlaw or ban these technologies, in the same way I don't advocate for criminalization of drugs. But I think companies managing these technologies have an onus to take steps to properly educate people about how LLMs work, and I think they also have a responsibility not to deliberately train their models to be sycophantic in nature. Regulations should go on the manufacturers and distributors of the dangers, not on the people consuming them.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#216Earlier quoted context omitted.
This is like arguing that we shouldn't try to regulate drugs because some people might "want" the heroin that ruins their lives. The existing "personalities" of LLMs are dangerous, full stop. They are trained to generate text with an air of authority and to tend to agree with anything you tell them. It is irresponsible to allow this to continue while not at least deliberately improving education around their use. Thi…
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 of caring, and that's simply not good enough.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#217Earlier quoted context omitted.
That's what the personality selector is for: you can just pick 'Efficient' (formerly Robot) and it does a good job of answering tersely? https://share.cleanshot.com/9kBDGs7Q
FWIW I didn't like the Robot / Efficient mode because it would give very short answers without much explanation or background. "Nerdy" seems to be the best, except with GPT-5 instant it's extremely cringy like "I'm putting my nerd hat on - since you're a software engineer I'll make sure to give you the geeky details about making rice." "Low" thinking is typically the sweet spot for me - way smarter than instant with…
I hate its acknowledgement of its personality prompt. Try having a series of back and forth and each response is like “got it, keeping it short and professional. Yes, there are only seven deadly sins.” You get more prompt performance than answer.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#218Earlier quoted context omitted.
Just set a global prompt to tell it what kind of tone to take. I did that and it points out flaws in my arguments or data all the time. Plus it no longer uses any cutesy language. I don't feel like I'm talking to an AI "personality", I feel like I'm talking to a computer which has been instructed to be as objective and neutral as possible. It's super-easy to change.
Care to share a prompt that works? I've given up on mainline offerings from google/oai etc. the reason being they're either sycophantic or so recalcitrant it'll raise your bloodpressure, you end up arguing over if the sky is in fact blue. Sure it pushes back but now instead of sycophanty you've got yourself some pathological naysayer, which is just marginally better, but interaction is still ultimately a waste of tim…
Sure:
Please maintain a strictly objective and analytical tone. Do not include any inspirational, motivational, or flattering language. Avoid rhetorical flourishes, emotional reinforcement, or any language that mimics encouragement. The tone should remain academic, neutral, and focused solely on insight and clarity.
Works like a charm for me.
Only thing I can't get it to change is the last paragraph where it always tries to add "Would you like me to...?" I'm assuming that's hard-coded by OpenAI.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#219Earlier quoted context omitted.
No matter how I tried, Google AI did not want to help me write appeal brief response to ex-wife lunatic 7-point argument that 3 appellant lawyers quoted between $18,000 and $35,000. The last 3 decades of Google's scars and bruises of never-ending lawsuits and consequences of paying out billions in fines and fees, felt like reasonable hesitation on Google part, comparing to new-kid-on-the-block ChatGPT who did not hes…
AI not writing legal briefs for you is a feature, not a bug. There's been so many disaster instances of lawyers using ChatGPT to write briefs which it then hallucinates case law or precedent for that I can only imagine Google wants to sidestep that entirely. Anyway I found your response itself a bit incomprehensible so I asked Gemini to rewrite it: "Google AI refused to help write an appeal brief response to my ex-wi…
I haven't mentioned anything about hallucinations. ChatGPT was solid on writing underlying logic, but to find caselaw I used Vincent AI (offers 2 weeks free, then $350 per month - still cheaper than cheapest appellant lawyer and I was managed to fit my response in 10 days).
That's fine, so Google sidestep it and ChatGPT did not. What point are you trying to make?
Sure I skip AI entirely, when can we meet so you hand me $35,000 check for attorney fees.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#220Earlier quoted context omitted.
No matter how I tried, Google AI did not want to help me write appeal brief response to ex-wife lunatic 7-point argument that 3 appellant lawyers quoted between $18,000 and $35,000. The last 3 decades of Google's scars and bruises of never-ending lawsuits and consequences of paying out billions in fines and fees, felt like reasonable hesitation on Google part, comparing to new-kid-on-the-block ChatGPT who did not hes…
What? AI assistants are prohibited from providing legal and/or medical advice. They're not lawyers (nor doctors).
Being a layer or a doctor means being a human being. ChatGPT is neither. Also unsure how you would envision penalties - do you think Altman should be jailed because GPT gave me a link to Nexus ?
I did not find any rules or procedures with 4 DCA forbidding usage of AI.