Introducing ProfG.AI

In this bonus episode, we get a behind the scenes look at how Prof G Media created a chatbot that sounds like Scott with the help of Spirito.ai. Check out the chatbot yourself at https://profg.ai/ Learn more about your ad choices. Visit podcastchoices.com/adchoices

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:01Scott Galloway?

  Support for the show comes from Northwest Registered Agent. Your business identity is everything that makes your business legitimate and professional. With Northwest Registered Agent, you don't just form a business, you start a complete foundation built for privacy, credibility, and growth. That includes registered agent service, a business address, operating agreement, domain, website, professional email, phone number, and built-in privacy. In other words, your home address, personal email, and phone number stay private. Don't pay hundreds or thousands of dollars for what you can get from Northwest for free. Visit northwestregisteredagent.com/profgfree and start using free resources to build something amazing. Get more with Northwest Registered Agent at northwestregisteredagent.com/profgfree.

• 0:48Speaker 01

  Your heart can tell you a lot about your health. Apple Watch Series 12 measures your heart rate every five seconds with the most accurate heart rate sensing in wearable. So your vitals app, now with heart rate variability, can tell you when something is off. And your readiness score can let you know when to rest and when to push. Hear the story in every heartbeat with Apple Watch Series 12. The features described are for wellness purposes only and not for medical use. iPhone 11 or later required. Based on Apple conducted study of heart rate accuracy, August 2026. Visit apple.com/aplewatchseries12.

• 1:27Scott Galloway?

  At PropG Media, we attempt to stay up on the latest technologies. And one way we do this is to actually use these technologies ourselves. In 2023, that means using, wait for it, AI tools. We've been experimenting with translating our podcasts into other languages, creating short videos for social media, and now we've developed an AI tool of our own that we'd like to share with you. It's called profg.ai. I know, that sounds scary. It's a chatbot similar to ChatGPT, only with a twist. Instead of chatting with OpenAI servers, you're chatting with a digital version of me. The catalyst here is see above.

• 2:09Scott Galloway?

  We want to learn about technologies, but also I receive dozens of emails each day from thoughtful people asking for advice. And as much as I'd like to respond, I can't. And so we tasked the team with coming up with a generative AI that could sound very similar and provide responses that felt sort of on point. This is a bit eerie because we took many of the office hours questions that we received, put them into PropG AI and found that the responses were pretty similar to what I would have said or how I would have responded. Anyways, with that, and here to explain how we actually made this tool and some of what we learned about the market along the way is PropG Media's editor in chief, Jason Stavers.

• 2:59Speaker 02

  When ChatGPT came out late last year, one of the first things we did at PropG Media was ask it to imitate Scott. We spent a lot of our time working with Scott on scripts and articles and other writing, and it would be incredible to have a digital Scott available to us 24/7. Plus, we thought it'd be fun. As Scott talked about last week on markets, OpenAI used some of his books to train GPT. So the bot can make an effort to imitate him, but you get a pretty generic vague version. We thought we could do better, so we built our own. Building a chatbot requires two primary components. The artificial intelligence portion that does the heavy lifting is what's called a large language model, or LLM.

• 3:44Speaker 02

  These are enormous statistical engines that take in a string of text and then predict what the most likely next string of text is going to be. That's a narrow skill, but as everyone who's used these tools has seen, it turns out to be a very powerful one. These systems are quite good at predicting the right answer to a question or how that answer might sound in the style of a pirate or written in computer code. However, because LLMs are just statistical engines, they can be a bit finicky to work with. That's where the second component comes in. The chatbot itself is an extra layer of software that sits between the user and the LLM. It's not really a translator, since the LLM knows every language.

• 4:29Speaker 02

  The chatbot is more like a diplomat. It takes the user's questions and instructions, and it gives the LLM more context for how it should respond. For example, most chatbots insert text before the user's message, along the lines of, "You are a helpful AI assistant that politely and accurately responds to user messages." The idea is to increase the statistical likelihood of the ideal response. So to make a digital Scott, we needed an LLM, and we needed a chatbot that could provide the LLM with enough context about how Scott thinks and writes that the LLM could accurately predict how he would respond to any question. To accomplish this, we turned to a London startup called spirito.ai.

• 5:14Speaker 02

  Spirito was founded by two engineers who left Meta just a few weeks before we met them, Dennis and Alice. I've asked them to join me and explain how we made a digital Scott. Dennis, one of the first decisions we had to make was which LLM we wanted to use. There's quite a few options available in the marketplace, right?

• 5:33Speaker 03

  Yeah, definitely. And it feels like there are new ones every week. Some are trained on specific knowledge domains, like Google's MedHome, which is specific to the medical field. Some are more general-purpose, like GPT-4 from OpenAI. Some are open-source, like Llama from Meta. So there's a bunch of different services out there, and there's a lot of variety in the street.

• 5:56Speaker 02

  Okay, so we decided to go with OpenAI's GPT. Why did that work for us?

• 6:01Speaker 03

  Yeah, so there were two kind of main criteria that we were kind of looking at here. So one is production capability and then the other is basically model performance. So on production capability, what we're really concerned about is basically like, can we even use this LLM at scale? A lot of the LLMs that exist out there are primarily for research purposes or academic purposes, or haven't yet been released, or they don't have the infrastructure to basically support what we're trying to do, which is build a large-scale consumer application. And on model performance, what we're really trying to evaluate is basically, how good is the LLM at this specific use case of building digital versions of creators? And ultimately, we felt that OpenAI's products basically were best at addressing both these criteria.

• 6:46Speaker 03

  And there are a couple other sort of bonus features as well, like fine tuning.

• 6:50Speaker 02

  So can you explain a bit more about what fine tuning is and how it's helpful to us?

• 6:54Speaker 03

  So basically, fine tuning is where you take a general-purpose model like GPT-4 and train it to better perform at specific tasks. You kind of show the LLM how to respond by giving it a bunch of data. And then later it'll use that data to basically like help itself improve on those sets of tasks. So in our case, what we did, we took GPT-3.5. We gave it a bunch of questions and then we gave it a bunch of responses in terms of how we'd want the ideal stock bot to respond. And in the end, we got a fine-tuned model that performed better than base GPT-4.

• 7:32Speaker 02

  Now, that's the LLM piece of the equation. But then we needed a chatbot that could provide the LLM with the context it would need to capture Scott. And there we had a great advantage because Scott has been writing prolifically for years and he's recorded hundreds of hours of podcasts. So what we needed the chatbot to do was to provide the LLM with just the portions of all that writing that would help it respond to each user question. Alice, can you explain how we went about that?

• 8:01Speaker 04

  LLM can only process a certain amount of tokens at a time, and Scott's prolific writing is definitely more than the limit there. So we use a strategy of chunking, embeddings, and similarity search to find the relevant text when someone asks a question. So let's go over each of these. Chunking is basically dividing the text into smaller pieces, which we can then embed and store in a database. The embeddings are important because in the next step, we use that embeddings to run a similarity search to find the chunks that are similar to a question, let's say, that is put into the chatbot. This helps us find the right slivers of information when someone asks the chatbot a specific topic.

• 8:41Speaker 02

  And then, how does the chatbot coach the LLM to use that material and sound like Scott?

• 8:47Speaker 04

  When we want our chatbot to sound like Scott, we can use a system prompt, which essentially guides the LLM into how to approach answering a question. And we want to balance styles such as tone, key phrases, maybe Scottisms. Instructions essentially act like a chatbot embodying Scott. And we're also going to feed in some extra context and how to handle that extra context that's passed in. So we need to be careful about all of these because adding too much information can cause the LLM to forget instructions, while adding too little information can cause it to perform suboptimally. So it's really part science, but also part art.

• 9:25Speaker 02

  Thanks, Alice. Thanks, Dennis. We've made our chatbot available at profg.ai, where you can check it out. It's an experiment, and still in the early stages. It handles some questions better than others, and it will get better as it answers more questions.

• 9:39Scott Galloway?

  So some fine print. One, I'm sure some of this will be wrong. And then again, I'm wrong quite a bit, but I'm sure some of this will not hit the mark. And we're open to feedback for how we make it better. And two, and most importantly, this cannot replace human relationships. And our hope is that this not only provides insight and guidance to people who I otherwise couldn't get back to, but that you use this information as a catalyst for reaching out. To potential friends, potential mentors, to increase your dialogue, your intimacy, and your contact with other people. Every digital analog of your life is a shittier version of your life.

• 10:22Scott Galloway?

  The digital facsimiles of relationships are just that. They're facsimiles. Find mentors. Discuss this with friends.

• 10:45Speaker 05

  Afternoon glare totally ruined my watch party for the big game. That's when my buddy recommended Blinds.com.

• 10:52Speaker 06

  With custom window treatments made to fit your style, space, and budget, customers who shop at Blinds.com experienced overwhelming satisfaction. Side effects may include a fuller, deeper night's sleep and a sudden urge to host the watch party again. Blinds.com isn't a medication, but it can improve how you feel about your home. Visit Blinds.com to order your free samples today.

• 11:15Speaker 07

  When you shop pickup at Kroger, you can expect the savings you love and fresh groceries selected just for you. Our associates are committed to getting every detail right, carefully handpicking your items, checking for quality and freshness, and packing your order with care. Because bringing you fresh, quality groceries is what we do best. And right now, enjoy $20 off your first online order of $75 or more. Restrictions apply. See site for details. Kroger. Fresh for everyone.