This is Five Minute Friday on a powerful chatGPT custom instructions hack.
Welcome back to the Super Data Science podcast. I am your host John Crone, from my machine learning company Nebula. I have the great pleasure of working with a number of world-class data scientists. One of those whose work I have mentioned on the show before is Sean Cosla, with both proprietary and open-source large language models. Sean has become quite a prompt engineer and an LLM Whisperer.
Recently, he tipped me off to a way that he has been leveraging ChatGPT’s custom instructions to automatically get improved responses from OpenAI’s Juggernaut GPT4 model. And although I haven’t tested it thoroughly, probably their GPT 3.5 model as well.
If you haven’t used custom instructions in ChatGPT before, here’s how you do it. When you’re in ChatGPT, go down to where your email address is in the bottom left-hand corner. It’s kind of three dots down there, and you select custom instructions from the options.
Then, there are these custom instructions you can fill in. So, there’s a box on what would you like ChatGPT to know about you to provide better responses. You can optionally fill that with information about you if you’d like. But for the purposes of today’s podcast episode, the hack doesn’t require that first field. Instead, we’re just going to make use of the second field, which is how would you like ChatGPT to respond.
So, here’s the hack. You can use this prompt that Sean put together himself in this field. It says, ‘I need you to help me with a task. First, come up with a detailed outline of how you think you should respond. Then, critique the ideas in this outline. Mention the advantages, disadvantages, and ways it could be improved. Then, use the original outline and the critiques you made to come up with your best possible solution. Overall, your tone should not be overly dramatic. It should be clear, professional, and direct. Don’t sound robotic or like you’re trying to sell something. You don’t need to remind me you’re a large language model. Get straight to what you need to say to be as helpful as possible. Again, make sure your tone is clear, professional, and direct, not overly like you’re trying to sell something.’
That’s his prompt. I’ve got it for you in the show notes so that you can copy and paste it yourself and adapt it to your own needs. Even feel free to share with me on social media if you come up with some derivations of this or you have your own kind of trick way of using these custom instructions to get awesome results. I’m always available. You know, tag me in a LinkedIn post or a public Twitter post. I’m always happy to have these kinds of conversations in public so that everyone can enjoy and add on.
So, in case it isn’t obvious, the first part of this prompt that Sean put together, the part about breaking the task down into parts and critiquing the ideas, allows the model to have an iteration over its initial inclinations, the original output that it prints out. And it allows it to come up with, in many circumstances, a much better output than its original inclination by doing this kind of self-critique to come up with the best solution. That’s why we have the first part in there. And then we have the second part in there because people who are listening to this podcast, data scientists, machine learning engineers, AI researchers, software engineers, other probably technically-minded people, we don’t need ChatGPT to have its regular persona, which can be maybe a little bit bubbly, telling us about how it’s a large language model and therefore hedging its bets on what it’s saying. We get that. We know that we’re professionals. So just give us something clear, professional, and direct. And yeah, we’ll get more, at least in my case, I’m getting more of the kinds of results that I’m looking for. Maybe you will as well.
That’s it for today’s episode. I hope this ChatGPT custom instructions hack reaps dividends in your daily workflows. Until next time, my friend, keep on rocking it out there. And I’m looking forward to enjoying another round of the Super Data Science podcast with you very soon.
