Everyone wants One Chat Solution. What is Chatbox?

  Powerful chatbot: Our chatbot is designed to be intuitive and easy to use, making it a great solution for businesses of all sizes. You can automate responses to frequently asked questions, provide personalized recommendations, and more.

  Seamless live chat: With our fully customizable live chat feature, you can connect with your customers in real-time and provide them with the support they need, when they need it. You can create a chat experience that's tailored to your brand, ensuring a seamless experience for your customers.

  Advanced analytics: Our advanced analytics features enable you to track the performance of your chatbot and live chat features, giving you valuable insights into what's working and what's not. You can make data-driven decisions that help you optimize your chat experience and improve your results.

   Last month, Dan Shipper (co-founder and CEO of Every) launched a chatbot trained on the Huberman Lab podcast, and I was blown away. I pinged Dan to see what it would take to build something like this for my newsletter content (as I was super-curious about the process, plus readers have been asking for it over the past couple of months, including just yesterday!), and by the next morning, Dan had a functioning chatbot 🤯

        Not only did Dan offer to build and launch the chatbot, he suggested that we use this opportunity to help people learn how to build their own. And that’s exactly what you’ll find below.

        Dan walks us through the basics of AI and GPT-3, how to set up an environment to play with the API, and how to train it on your own data. No coding background necessary. I found this incredibly interesting, and, as Dan points out below, “the best way to prepare for this fast-approaching future is to dive in and get your hands dirty.” Let’s dig in.

You can find Dan Shipper on Twitter, LinkedIn, and especially make sure to subscribe to Every, where he shares his ongoing research into all things AI, tech, and personal development.

    Lenny’s Newsletter is great, but it’s inherently one-sided. It talks to you, but you can’t talk back. Wouldn’t it be awesome if you could ask      Lenny’s Newsletter a question?

   Well, now that’s possible. 

    Over the course of last week I built an AI-powered chatbot for Lenny that uses his entire newsletter archive to answer any question you have about product, growth, and startups. It’s built with GPT-3 and it took a couple hours to do, end to end. In this post, I’ll break down exactly how the Lenny Bot works so you can learn to build one yourself.

Preamble: GPT-3 vs. ChatGPT

You’ve probably heard of both GPT-3 and ChatGPT. Maybe you use those terms interchangeably, or maybe you’re not really sure what the difference is. It’s worth taking a minute to understand how they differ.

GPT-3 and ChatGPT are both “large language models.” These are machine-learning models that are very good at generating natural-sounding text, code, and more. They’re trained using large data sets of text, and this helps them get very good at lots of natural-language tasks, like answering questions, writing marketing copy, and holding conversations. So what’s the difference between them? And why is it important?

GPT-3 is a general-purpose language model—it can hold conversations, write code, complete a blog post, do translation tasks, and more. You can think of it like a flexible know-it-all that can expound on any topic you want. 

ChatGPT is a version of GPT-3 that’s been turned into a friendly, inoffensive extrovert. Basically, it’s been specifically trained to be good at holding conversations. OpenAI does this by repeatedly holding conversations with the model and then rewarding it for good responses and punishing it for bad ones—a process called Reinforcement Learning from Human Feedback. 

You’d think since we’re building a chatbot we’d use ChatGPT, right? Unfortunately not. OpenAI hasn’t created a way for us to interact with the ChatGPT model directly—you can only use it through the ChatGPT web app. So it’s not suitable for our purposes.

We want to be able to interact with the model directly, not through an intervening app. So instead we’ll use GPT-3 for our explorations. It’ll give us all the power and flexibility we need to build a chatbot. 

We’ll do it in two ways: using OpenAI’s Playground to start, and with a little bit of code after that. The Playground is a web app that lets you prompt GPT-3 directly and get responses back, making it a great place for us to experiment.

Let’s start there and see how things go.

The basics of GPT-3

The really basic way to explain GPT-3 is that it likes to finish your sentences for you. You provide it with a starting set of words, and it tries to figure out the most likely set of words that follow from your input. You can provide any string of words. It’s very flexible and can talk about anything you want, from product management to astrophysics.

The set of words you provide is called a prompt, and the answer you get back from GPT-3 is called a completion.

Below is a simple example in the GPT-3 Playground. The non-green text is what I typed in as a prompt, and the green text is what GPT-3 returned as the completion: