Journalism The story I found most compelling in terms of its potential impact on the journalism industry is how GPT-4 itself can increase consumers’ engagement. People are going to like news more when they have more control over how it’s delivered— and, as a result, I suspect they’ll want more of it. Extra! Extra! Ask all about it! Delivering highly personalized user experiences has driven internet development for more than thirty years. Platforms like YouTube, Facebook, and Amazon all keep close tabs on the content you consume, then use it to recommend more content they think you will like. (Not to mention the pair of sneakers you first looked at two years ago that continues to follow you from website to website like a lost, lonely puppy.) News media websites use personalization, too, and as I contin- ued to submit various questions to GPT-4 about AI’s potential impact on journalism, “personalization” was a recurring theme. When I asked GPT-4 how this personalization would work, here’s what it replied: Reid: To make news media websites more personalized, what data will these websites use to analyze readers’ behavior and preferences? GPT-4: News media websites will use data such as the reader’s location, the type of device they are using, their browsing history, and the articles they have previously read or interacted with. They can also analyze which articles the reader has shared on social media, how long they spend on the website, and which sections they visit most frequently. Additionally, data on the reader’s age, gender, and interests can be used to personalize con- tent. This data can be obtained through cookies, surveys, and user accounts, among other methods. By analyzing 85