Looking for specific tips and tricks to break AI out of formal/corporate writing patterns. Tried style mimicry (‘write like Hemingway’) and direct requests (‘be more creative’) - both fell flat. What works?
Should I be using different AI models ( I am using GPT and Claude)? The base models output an enormous creative storm, but somehow the RLHF has partially lobotomized LLMs such that they always seem to output either cheesy stereotypes or overly verbose academise/corporatespeak.
Edit: ChatGPT and Claude are both fine IMO. Claude has a better ear for language, but ChatGPT’s memory is very useful for letting you save info about your preferences, so I’d say they come out about even. For ChatGPT in particular, you’ll want to put whatever prompt you ultimately come up with into your custom instructions or its memory; that way all new conversations will start off pre-prompted.
In addition to borrowing others’ prompts as Nathan suggested, try being more specific about what you want (e.g., ‘be concise, speak casually and use lowercase, be sarcastic if i ask for something you can’t help with’), and (depending on the style) providing examples (ETA: e.g., for poetry I’ll often provide whichever llm with a dozen of my own poems in order to get something like my style back out). (Also, for style prompting, IME ‘write in a pastiche of [author]’ seems more powerful than just ‘write like [author]’, though YMMV).
I have found that they mirror you. If you talk to them like a real person, they will act like a real person. Call them (at least Claude) out on their corporate-speak and cheesy stereotypes in the same way you would a person scared to say what they really think.
The two suggestions that come to mind after brief thought are:
Search the internet for prompts others have found to work for this. I expect a fairly lengthy and complicated prompt would do better than a short straightforward one.
Use a base model as a source of creativity, then run that output through a chat model to clean it up (grammar, logical consistency, etc)
Looking for specific tips and tricks to break AI out of formal/corporate writing patterns. Tried style mimicry (‘write like Hemingway’) and direct requests (‘be more creative’) - both fell flat. What works?
Should I be using different AI models ( I am using GPT and Claude)? The base models output an enormous creative storm, but somehow the RLHF has partially lobotomized LLMs such that they always seem to output either cheesy stereotypes or overly verbose academise/corporatespeak.
Edit: ChatGPT and Claude are both fine IMO. Claude has a better ear for language, but ChatGPT’s memory is very useful for letting you save info about your preferences, so I’d say they come out about even.
For ChatGPT in particular, you’ll want to put whatever prompt you ultimately come up with into your custom instructions or its memory; that way all new conversations will start off pre-prompted.
In addition to borrowing others’ prompts as Nathan suggested, try being more specific about what you want (e.g., ‘be concise, speak casually and use lowercase, be sarcastic if i ask for something you can’t help with’), and (depending on the style) providing examples (ETA: e.g., for poetry I’ll often provide whichever llm with a dozen of my own poems in order to get something like my style back out). (Also, for style prompting, IME ‘write in a pastiche of [author]’ seems more powerful than just ‘write like [author]’, though YMMV).
I have found that they mirror you. If you talk to them like a real person, they will act like a real person. Call them (at least Claude) out on their corporate-speak and cheesy stereotypes in the same way you would a person scared to say what they really think.
The two suggestions that come to mind after brief thought are:
Search the internet for prompts others have found to work for this. I expect a fairly lengthy and complicated prompt would do better than a short straightforward one.
Use a base model as a source of creativity, then run that output through a chat model to clean it up (grammar, logical consistency, etc)