![]() The answer is to modify GPT and work with it directly, rather than go through ChatGPT’s higher-level interface. ![]() With that basic primer on how ChatGPT works, it’s easy to see why it can’t tell your customer if their flight was delayed or if they can upgrade to first class. One token at a time, it figures out what is the next logical thing it should output.Īs we’ll see in a minute, context windows are the key to evolving ChatGPT’s capabilities. When you prompt ChatGPT, your text is broken down into a sequence of tokens as input into the neural network. By training on such a large corpus of data, GPT has been able to infer an astonishing amount about how to converse like a human and appear intelligent. While there’s no shortage of in-depth discussion about how ChatGPT works, I’ll start by describing just enough of its internals to make sense of this post.ĬhatGPT, or really GPT, the model, is basically a very large neural network trained on text from the internet. I’ll walk through how to build a real-time support agent, discuss the architecture that makes it work, and note a few pitfalls. ![]() In this post, I’ll show how streaming and ChatGPT work together. What is the right tool for the job here? Event streaming is arguably the best because its strength is circulating feeds of data around a company in real time. That means that data engineering now has to happen at prompt time, so the data flow problem shifts from batch to real-time. In this paradigm, when you want to teach the model something specific, you do it at each prompt. And it is why ChatGPT is helpful for so many things out of the box. This means that services like those provided by OpenAI and Google mostly provide functionality off reusable pre-trained models rather than requiring they be recreated for each problem. Here, the model is built by taking a huge general data set and letting deep learning algorithms do end-to-end learning once, producing a model that is broadly capable and reusable. With large language models, the relationship is inverted. Since training is usually done in batch, the data flow is also batch and fed out of a data lake, data warehouse, or other batch-oriented system. Most of the problem-specific smarts are baked in at training time. Once the training is complete, you have a one-off model that can do the task at hand, but nothing else. You take a specific training data set and use feature engineering to get the model right. In traditional machine learning, most of the data engineering work happens at model creation time. Large language models have changed the relationship between data engineering and model creation. Surprisingly, how you do this doesn’t follow the standard playbook for machine learning infrastructure. The fundamental obstacle is that you, the airline company, need to safely provide timely data from your internal data stores to ChatGPT. Your personal data is (thankfully) not available on the public internet, so even Bing’s implementation that connects ChatGPT with the open web wouldn’t work. This isn’t something that can be “fixed” by more innovation at OpenAI. Well, if that’s a general policy of the airline, that information is probably available on the internet, and ChatGPT might be able to answer it correctly.īut what about a more personal question, like “Is my flight delayed?”, or “Can I upgrade to first class?”, or “Am I still on the standby list for my flight tomorrow?” It depends! First of all, who are you? Where and when are you flying? What airline are you booked with?ĬhatGPT can’t help here because it doesn’t know the answer to these questions. Your customer might have a question about how much it costs to bring skis on the plane. Imagine you’re an airline, and you want to have an AI support agent help your customers if a human isn’t available. What do I mean by that? Let me give you an example of a scenario every company is thinking about right now. But how do you go beyond just messing around and using it to build a real-world, production application? A big part of that is bringing together the general capabilities of ChatGPT with your unique data and needs. By this point, just about everybody has had a go playing with ChatGPT, making it do all sorts of wonderful and strange things.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |