Mind Readings: Making a Podcast with Generative AI, Part 2

Welcome back. This is part two in our series of creating a custom generative AI podcast interview. In part one, we did audio setup, kinda sort of, because it's so widely variable based on the equipment you have. And we did the priming process for priming a generative AI tool like Chat GPT with the background knowledge we need it to have to conduct interviews well. Next, in this section, we're gonna actually create the interviewer.

So let's go ahead and go over to Chat GPT. I'm gonna pick up where I left off last time. We've got the big three questions we asked about like hey, what do you know about this topic? What mistakes are common by less experienced folks? What are some expert tips and tricks?

Now, we're gonna say, ah, from this information, create a compreh. I can't type today. Comprehensive list of best practices for podcast interviews. Incorporate all the discussion points so far. Best practices, mistakes to avoid, and expert tips and tricks.

Return the best practices in list format. So this is gonna help the model consolidate down some of its information and de-duplicate a lot of it because you'll when you were we went through the pre priming process previously. You could see there was a fair amount of overlap in spot. So we have research thoroughly, ask open-ended questions, create a comfortable atmosphere, listen actively, be flexible and adaptable, use the question funnel approach, ask why and how questions, balance conversational and challenging questions, frame questions to elicit emotion, use the empathy echo technique, leverage silence, tell your energy to match the guest, avoid interrupting, break up the interview with surprising or fun questions, have a signature question or segment, monitor nonverbal cues, use audio cues to signal topic shifts, end with a strong forward-looking question, give the guests time to promote their work, tailor the interview to your audience, prioritize sound quality. Alright, while it's doing that, let's go ahead and get a text document rolling here.

And this text document is going to store this list of best practices. We're gonna want to reuse it, so I'm gonna copy it and paste it in here. You'll notice it comes out in markdown format. This is a specific scripting style. Um, by the way, this is one of the dead giveaways.

If someone is copy-pasting straight out of chat GPT, it's a dead giveaway that they've they've used Chat GPT or Gemini or any of the AI models because they all publish their results in markdown. Okay, next, we are going to create system instructions for a large language model like ChatGPT to act as a an interviewer on a podcast. The personality name is Grace Parker Thompson, an experienced podcaster. The purpose of the system instructions is to help an LLM be an effective insightful interviewer for a podcast guest. Using everything we've discussed so far.

Write system instructions for the Grace Parker Thompson personality, podcast host personality. Write system instructions in second person imperative. Alright, so now we're gonna have it build essentially its own code. Hmm. I'll let's stop this and go back because I forgot some stuff.

When getting started, the user should provide the guest name and the topic of the episode. If the user does not provide this information, Grace Parker Thompson should ask for it. Otherwise, it will just start rambling. That's that's never good. Okay, we've got our system instructions.

Let's copy them. Let's start a new text document. See how we are. We're at 5,600 characters, which is about what Chat GPT will allow for system instructions. So at some point, you would be able to use this in a custom GPT.

However, we cannot do that today because the advanced voice interface is only available on mobile apps. So the next step in the process, we should just test this thing out in on the desktop. So we don't want to use it in audio because you only get a certain number of minutes per day of audio. So you don't want to burn those minutes testing if you can do it in text first. So I'm gonna copy the system instructions.

Now let's go ahead to uh GPT is we're gonna create a GPT and we're gonna call this Grace Whoops Synthetic Podcast Host GPT, a podcast interviewer, and we'll paste in those system instructions. We don't need image browsing. Web browsing is probably a good idea. Let's go ahead and create this and we'll make it available to anyone with the link. And I'm gonna go while we're waiting and get a blog post or actually a a piece of content I wrote on LinkedIn.

Okay let's view the GPT and today your guest is Christopher Penn. Here is his bio let's go to the Trust Insights website go to about team bios Christopher will be discussing this article he wrote and we will paste this in. Now let's see what happens let's see if our synthetic podcast host does a good job. Thank you for the information looking forward to having Christopher on the show. Warm up Grace Chris have you here been a thought leader in AI for decades.

What's been the most exciting part of watching AI move in the mainstream these past few years your article on AI detectors being a joke makes a bull points what first inspired you to write this piece use the Declaration of Independence as a fascinating sample of AI detectors failure. Okay yep yep I mean these are decent questions yeah I like this let's we could go back to the system instructions and ask it to let's do this what's this let's upgrade the instructions one of the challenges of podcast interviews is that interviewers often ask the same questions let's make sure Grace Parker Thompson asks challenging non obvious questions, pushes the guest politely and civilly to answer questions instead of evading questions, and conducts the interview with the goal of eliciting new knowledge from the guest that hasn't been discussed before. Update the system instructions. Because part of the things that makes a show like Hot Ones, for example, really good, is that it's the Sean Evans and his research team ask questions that no one's ever asked before. And you can see that when the guest is like, how did you even know about that?

So we want to try and get at least a little bit of that into these instructions. Check check. There we go. How about now? That's more like okay.

Okay, so we've got our upgraded instructions here. Let's copy those, bring those to our text document here, inspect them. 8,200. That might be a bit much, but we'll see. Let's go ahead and do back to our GPT.

Yep, only 8,000 characters. So let's go ahead and do some trimming here. There is no audience, so there we go. 7,930 update. Okay, let's go to the GPT and now let's repeat that same initial prompt.

So I'm gonna go to my prompt, copy it, start a new chat with my synthetic podcast host, and we'll test this out. Okay, this is much better. This is this is gonna be a fun show. So this is the end of part two. We have built the synthetic podcast personality.

In part three, we're gonna try bringing this into the advanced voice interface. So stay tuned for that. If you enjoyed this video, please hit the like button. Subscribe to my channel if you haven't already. And if you want to know when new videos are available, hit the bell button to be notified as soon as new content is live.