OpenAI’s latest ChatGPT model, OpenAI o1, is a powerful reasoning unit. This new edition doesn’t just provide answers. He pauses, ponders and ponders before answering. It’s like having a conversation with a thoughtful friend who carefully considers his words.
According to OpenAI, this internal reasoning process leads to more considered responses. For founders and entrepreneurs using AI in their businesses, ChatGPT o1 is a game changer.
How to request the new ChatGPT: tips from OpenAI
Keep prompts simple
What you learned about writing in school is becoming less relevant. For best results online, formal and complicated is not the way, but simple and straightforward. This is the same with the new ChatGPT, which thrives on clarity. Ditch the long instructions and keep it short.
Instead of “Can you come up with a list of 20 possible product names for a new eco-friendly water bottle, considering factors such as environmental impact, target demographics, and current market trends?” try “5 catchy names for an eco-friendly water bottle.” The model will understand what you are looking for and fill in the gaps. Like a human, he will understand the context and read between the lines.
Let it think for itself
When a junior team member joins your company, you teach them to follow your procedures. When a senior leader takes over, you expect them to have theirs. ChatGPT wants to be the senior leader, having free control over your tasks, using its own methods to find the right answer.
This means the Chain of Thought (CoT) prompts are out. You don’t need to tell him to “think step by step” or “explain your reasoning”. ChatGPT is already on it. The new ChatGPT does its own mental gymnastics, and responses can take longer than it thinks. Just ask the question and let it go.
Separate your instructions
If you were advising a person, you would pause when you spoke. You would separate the email instructions with paragraph sections and line breaks. It’s similar here.
The new ChatGPT wants you to use delimiters. These include triple quotes, XML tags or simple section titles – they’re like signposts for AI. Using them helps ChatGPT understand which part is which, preventing confusion.
You have many options for delimiters: Markdown headers, dashes, asterisks, numbered sections or letters. Break up your prompts, break up your examples, and make sure your instructions aren’t confusing.
Don’t overload the conversation
Giving a person too much information would cause them to shut down. Your stylist doesn’t need your life story any more than you want your hair. Your accountant doesn’t need every detail of your career, just what’s relevant to your accounts today. Apply similar thinking here.
RAG, or Retrieval Augmented Production, is when you feed additional information to ChatGPT. But with the new model, less is more.
OpenAI warns that overloading ChatGPT with data can lead to overthinking and slower responses. Where once you could throw pages of examples at a simple task, now you should only include the most relevant bits.
How to request new ChatGPT for best results
These changes mean rethinking how you use ChatGPT. It’s no longer about crafting the perfect, long message. These are short, targeted questions. Adjusting your prompting style will lead to faster and more accurate responses.
OpenAI emphasizes that the key to success with o1 is trusting the model’s ability to understand context and generate relevant responses without excessive guidance.
When technology moves so fast, you have to keep learning. Get the most out of the new ChatGPT with these four simple steps.