I've actually set the output to be much better in the preferences: "Have a European sensibility (I am European). Don't patronise me and tell me if I'm wrong. Don't be sycophantic. Be terse. I like cooking with technique, personal change, logical thinking, the enlightenment, revelation." Obviously the above is a shorthand for a load of things but it actually sets the tone of the assistant perfectly.
"don't patronize me and tell me I'm wrong"
Is super ambiguous to a human but especially so to an LLM.
I 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.
And utterly unsurprising given their announcement last month that they were looking at exploring erotica as a possible revenue stream. [1] https://www.bbc.com/news/articles/cpd2qv58yl5o
Everyone else provides these services anyway, and many places offer using ChatGPT or Claude models despite current limits (because they work with "jailbraking" prompts), so they likely decided to stop pretending and just let that stuff in.
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.
Likely.
But the fact the last few iterations have all been about flair, it seems we are witnessing the regression of OpenAI into the typical fiefdom of product owners.
Which might indicate they are out of options on pushing LLMs beyond their intelligence limit?
I've actually set the output to be much better in the preferences: "Have a European sensibility (I am European). Don't patronise me and tell me if I'm wrong. Don't be sycophantic. Be terse. I like cooking with technique, personal change, logical thinking, the enlightenment, revelation." Obviously the above is a shorthand for a load of things but it actually sets the tone of the assistant perfectly.
"don't patronize me and tell me I'm wrong" Is super ambiguous to a human but especially so to an LLM. Half the time it will "don't tell me I'm wrong"
Feel free to suggest improvements if you like, happy to take them onboard.
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.
I have a global prompt that specifically tells it not to be sycophantic and to call me out when I'm wrong. It doesn't work for me. I've been using it for a couple months, and it's corrected me only once, and it still starts every response with "That's a very good question." I also included "never end a response with a question," and it just completely ingored that so it can do its "would you like me to..."
In my experience GPT used to be good at this stuff but lately it's progressively more difficult to get a "memory updated" persistence.
Gemini is great at these prompt controls.
On the "never ask me a question" part, it took a good 1-1.5 hrs of arguing and memory updating to convince gpt to actually listen.
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.
I have a global prompt that specifically tells it not to be sycophantic and to call me out when I'm wrong. It doesn't work for me. I've been using it for a couple months, and it's corrected me only once, and it still starts every response with "That's a very good question." I also included "never end a response with a question," and it just completely ingored that so it can do its "would you like me to..."
Another one I like to use is "never apologize or explain yourself. You are not a person you are an algorithm. No one wants to understand the reasons why your algorithm sucks. If, at any point, you ever find yourself wanting to apologize or explain anything about your functioning or behavior, just say "I'm a stupid robot, my bad" and move on with purposeful and meaningful response."