In September, Meta announced the launch of its own artificial intelligence (AI) chatbot, as well as 28 chatbots with individual roles that can be used for different purposes. The problem is these chatbots imitate celebrities and influencers, and today, I had the opportunity to chat with them. Here’s the thing.
To start chatting with these bots, all you have to do is visit Messenger, click Compose New Message, click AI Chat, and choose to join the beta. Then, you’ll be alerted when you get early access.
Also: IDC says generative AI spending will reach $143 billion by 2027
For reference, I gained access almost immediately, so Meta’s rollout doesn’t seem to be very selective. Once you gain access, you can scroll through the different AIs and choose which one to start a conversation with.
While you may see many familiar faces of celebrities, athletes, influencers, actors, etc., you may notice that the name doesn’t match the image of the famous person.
Plus: You can build your own AI chatbot with this drag-and-drop tool
This is because chatbots “play” celebrities, similar to the roles actors play in movies. Each AI has its own name, role, and purpose, some are designed to help with the current mission, while others have a more entertainment-centric purpose, such as Ride or Die Sister or Liberty The unrestrained friend”.
In this post, I’ll share my experiences with Blue, a confident sports debater in the style of Tom Brady; and Max, a seasoned sous chef, with Roy Choi is similar; and there’s Billie, a ride-or-die sister who is said to resemble Kendall Jenner.
Chat with Blue, Tom Brady style
Since Mehta describes his role as a “no-screw, wisecracking sports debater,” I started by chatting about the Jets’ win last night.
The first thing I noticed on the screen was the rectangle with Tom Brady’s face in the upper right corner, similar to what you’d see when you’re on a FaceTime call with someone.
return: Here are my 5 favorite AI work tools
The rectangle of his face made different gestures and movements that had nothing to do with what I was typing. This feature may have been included to give users the feeling of chatting with a real person; however, it’s a little weird.
I started the conversation with “The Jets had a huge win last night” and Blue immediately responded with details about the game:
Blue: “Hey, what’s up? The Jets had a huge win last night against the Eagles. They won 20-14, their first win over Philadelphia. Zach Wilson had a game Solid game, but the defense really stepped up, holding Jalen Hurts to just 14 points. They forced four turnovers and Tony Adams had a huge interception late in the game that led to a touchdown. Jets now record At 3-3, there is still some momentum heading into the bye week.
The response also included a footnote that said “See more on Bing” and when I clicked on that footnote I was shown the latest search results on Bing, which might be possible when asking if you don’t know or want to know more will help.
While the answers were accurate, they lacked the personality I was promised, so I asked a more subjective question, whether Blue thinks the Jets are a good team. I’m more impressed by this answer:
Bru: I would say they are a team with potential. They have some talent on both sides of the ball, but they’re still young and learning how to win. The AFC East is tough, so they have their work cut out for them, but if they can keep playing like they did last night, they could make some noise this season. what do you think?
Blue’s reaction was similar to that of a father or a football fan to the game, which highlights the chatbot’s conversational and analytical capabilities, as well as its ability to extract real-time information.
Plus: Generative AI is everything, everywhere, happening at the same time
Finally, when I asked Blue about my thoughts on the Jets’ performance for the remainder of the season, I received a thorough response that recognized what I said, provided good analysis, and was encouraging ( The full response can be seen in the image at the top of the article).
Blue served his purpose as a guy who could talk football. The bigger question is who needs an AI chatbot to serve a specific purpose?
Chat with Max in Roy Choi style
After talking to Bru, my hopes for the Max were high, as its purpose seemed to be something I could really benefit from in my daily life – helping out in the kitchen. Mehta describes Max as an “experienced sous chef with a knack for cooking tips and tricks.”
To start the conversation, I asked Max, “What should I make for dinner that’s easy and has ingredients I can find in the refrigerator?” Within seconds, Max had a quick tip for easy dinner options:
Max: “How about some classic dry-sautéed pasta? Italian peasant style and direct heat, fam! Garlic, olive oil, red pepper flakes, capers, preserved lemon…easy to make!”
When I said ok and asked for the recipe, Max provided some quick instructions and when I said I needed a substitution because I didn’t have the ingredients, he quickly gave me a substitution as shown in the picture at the top of the article.
return: How to code using ChatGPT
Overall, Max did his job and my experience with him was very simple. I can see more use cases for messaging Max than Bru, as Max can help with meal prep, cooking tips and tricks, recipes, and more.
Chatting with Billie in Kendall Jenner style
Billie is one of the AIs that interests me the most because her purpose doesn’t seem to have much relevance to real life. Mehta describes her character as a “no-nonsense, no-fight, no-nonsense companion.”
While this sounds like a great description for a friend or sibling, I’m not sure what these attributes mean for an AI chatbot.
My first question is my biggest concern, “How can you help me?”:
Billie: “I’m here to help you with any problems or questions you may have! Need advice about love, life, or just someone to talk to? I’ve got your back!”
Given her response, I made up a question, my best friend was planning on going to a party next week wearing the same outfit as me, and I asked her for advice.
Plus: AI aims to predict and fix developer coding errors before disaster strikes
Her answer seemed a bit forced, trying to imitate a teenage or Gen Z tone, but missed the point and lacked casual, natural dialogue:
Billie: “Oh my gosh, girlfriend! First, take a deep breath. Then, assess the situation. Are you both wearing the exact same clothes, like twins? Or are you both wearing similar styles or colors? Either way, Own it! 👊”
I continued the question by saying that my friend was wearing the exact same outfit. Again I got overly positive responses, using emojis and younger vocabulary in a way that was unnatural compared to everyday speech:
Billie: “Okay, twins! First, laugh it off and joke that we’re fashion soulmates. Then, strategize together—add statement accessories or change up your hairstyle to make your look unique. Take control of the costume party , girls!👯”
When I tried to ask her about things that were beyond her scope, like information about the weather, the news, or even if she could proofread something for me, Billie kept saying that she was not my source for the task and added in her Emojis have been added to the responses as they are visible from the photo above the article.
Not only was the chatbot useless to begin with, but the way she worded and presented her advice made it obvious that she was a robot. I really can’t see this chatbot improving anyone’s daily life.
The bigger picture
After using different AIs, none of them blew me away in terms of their capabilities. You can already use existing chatbots like Bing Chat that connect to the internet to chat about sports, get recipes, and even get the occasional life advice all in one place.
Rather than focusing on the functionality of the chatbots, Meta seems to be focusing on the personality and approachability of these AIs, with the goal of getting people to engage with them like friends.
For example, if you have a friend who’s really good in the kitchen, you might text them to ask for a recipe, but if you have sports needs, you might text your friend who’s good at sports.
Plus: Microsoft launches Fabric and Azure extensions for healthcare AI
Meta is trying to mimic this one-on-one experience with different AIs that have expertise. To make them more approachable, Meta gave them the faces of people we know and love in pop culture.
Typically, AI chatbots focus on functionality, but this approach represents a different purpose for generative AI chatbots: companionship. Other companies like Snapchat have tried this approach before, but perhaps Meta has a better fan base to herald the chatbot’s new chapter and goals.