It is truly stupid that they are trying to make it more human-like. They should have added a radio button to turn off these sort of customizations because it doesn't help some of us. Just pisses me off. It is supposed to be an answering machine, not some emotional support system.
GPT-5.1: A smarter, more conversational ChatGPT
301–310 of 766 posts
Re: GPT-5.1: A smarter, more conversational ChatGPT
#302Sadly, 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.
Can you give an example of things it refuses to answer in that subject?
Re: GPT-5.1: A smarter, more conversational ChatGPT
#303WE DONT CARE HOW IT TALKS TO US, JUST WRITE CODE FAST AND SMART
Dude, why are you mad?
Re: GPT-5.1: A smarter, more conversational ChatGPT
#304It is truly stupid that they are trying to make it more human-like. They should have added a radio button to turn off these sort of customizations because it doesn't help some of us. Just pisses me off. It is supposed to be an answering machine, not some emotional support system.
They do have that option to customize its personality. One of the choices is to have it be robotic and straight to the point.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#305I don't want a more conversational GPT. I want the _exact_ opposite. I want a tool with the upper limit of "conversation" being something like LCARS from Star Trek. This is quite disappointing as a current ChatGPT subscriber.
Zachary Stein makes the case that conferring social statuses to Artificial Intelligences is a ex-risk. https://cic.uts.edu.au/events/collective-intelligence-edu-20...
Re: GPT-5.1: A smarter, more conversational ChatGPT
#306If you don't have access here are some sample conversations: https://chatgpt.com/share/6914f65d-20dc-800f-b5c4-16ae767dce... https://chatgpt.com/share/6914f67b-d628-800f-a358-2f4cd71b23... https://chatgpt.com/share/6914f697-ff4c-800f-a65a-c99a9d2206... https://chatgpt.com/share/6914f691-4ef0-800f-bb22-b6271b0e86...
cool
Re: GPT-5.1: A smarter, more conversational ChatGPT
#307Sadly, 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.
do you have this issue in codex cli or just in chatgpt web? Just curious, I have ran into that type of thing in chatgpt.com but never in codex.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#308Is anyone else tired of chat bots? Really doesn't feel like typing a conversation every interaction is the future of technology.
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.
“Computer, fire torpedos on my mark.”
“As someone who loves their tea hot, I’ll be sure to get the torpedos hot and ready for you!”
Re: GPT-5.1: A smarter, more conversational ChatGPT
#309Maybe I am wrong but this release make me think OpenAI hit a wall in the development and since they can't improve the models, they started to add gimmicks to show something new to the public.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#310It is truly stupid that they are trying to make it more human-like. They should have added a radio button to turn off these sort of customizations because it doesn't help some of us. Just pisses me off. It is supposed to be an answering machine, not some emotional support system.
Also, I wish there was a setting to disable ChatGPT in its system prompt to have access to my name and location. There was a study on an LLM(s) (not image gen) a couple of years ago (I can't find the study now) which showed that an unfiltered OSS version had racist views towards certain diasporas.