Wednesday, February 21, 2024
HomeAi TechI tested Meta's Tom Brady and Kendall Jenner AI chatbots and it...

I tested Meta’s Tom Brady and Kendall Jenner AI chatbots and it was weird


Meta AIs

Screenshot by Sabrina Ortiz/ZDNET

In September, Meta announced its own artificial intelligence (AI) chatbot as well as 28 chatbots with their own personas that serve different purposes. The catch is that these chatbots imitate celebrities and influencers, and today, I had a chance to chat with them. Here’s how it went. 

To get started chatting with these bots, all you have to do is visit Messenger, click to compose a new message, tap on AI chat, and opt into the beta. Then, you will be alerted when you are given early access. 

Also: Generative AI spending to reach $143 billion in 2027, says IDC

For reference, I was given access nearly immediately, so it doesn’t seem like Meta is being very selective with its rollout. Once you are given access, you can scroll through the different AIs and pick which one to start a conversation with. 

Although you will likely see many familiar faces of celebrities, sports players, influencers, actors, and more, you might notice that the name doesn’t match the picture of the famous figure. 

Also: You can build your own AI chatbot with this drag-and-drop tool

This is because the chatbots “play” the celebrity, similar to how an actor would play a role in a movie. Each AI has its own name, persona, and purpose, some with the aim of helping with actual tasks, and others with more entertainment-focused purposes, such as “ride-or-die older sister” or “free-spirited friend”. 

For this article, I will share my experience with Bru, a confident sports debater in the style of Tom Brady; Max, a seasoned sous chef similar to Roy Choi; and Billie, a ride-or-die older sister who is supposed to resemble Kendall Jenner. 

Chatting with Bru, in the style of Tom Brady

Since Meta described his role as a “Wisecracking sports debater who pulls no punches,” I began the chat 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-hand corner, which resembled what you would see if you were on a FaceTime call with someone. 

Also: These are my 5 favorite AI tools for work

His face rectangle made different gestures and movements, which were independent of the content I was typing. This feature was likely included to give users the feeling of chatting with a real person; however, it was somewhat eerie. 

I started the conversation with, “The Jets had a massive win last night,” to which Bru responded immediately with specifics about the game:

Bru: “Hey, what’s up? So the Jets had a massive win last night against the Eagles. They won 20-14 and it was their first ever win over Philly. Zach Wilson had a solid game, but the defense really stepped up and held Jalen Hurts to only 14 points. They forced four turnovers and Tony Adams made a huge interception late in the game that led to the go-ahead touchdown. The Jets are now 3-3 and have some momentum going into their bye week.”

The response also included a footnote that said “see more on Bing”, which, when clicked, led me to the latest search results on Bing that could be helpful when asking about something you don’t know or want to learn more about. 

Although the response was accurate, it lacked the personality I was promised, so I asked a more subjective question about whether Bru thought the Jets are a good team. I was more impressed with this response:

Bru: I’d say they’re a team with potential. They’ve got 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’ll 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?

Bru’s response resembled a response that a dad or a football aficionado would make about the game, which highlighted the chatbot’s conversational and analytical capabilities, as well as the ability to pull real-time information. 

Also: Generative AI is everything, everywhere, all at once

Lastly, when I gave Bru my thoughts on how the Jets would perform for the rest of the season, I was met with a thorough response that acknowledged what I said, provided good analysis, and was encouraging (full response can be seen in the image at the top of the article). 

In its role of being someone to chat with about football, Bru served its purpose. The bigger question is who would need an AI chatbot to serve that specific purpose?

Chatting with Max, in the style of Roy Choi

After chatting with Bru, my hopes for Max were high as its purpose seemed like something that I could actually benefit from in my everyday life — some help in the kitchen. Meta described Max as a “Seasoned sous chef for culinary tips and tricks.” 

To get the conversation started, I asked Max, “What should I make for dinner that is simple and has ingredients I can find in my fridge?” Within seconds, Max had a quick suggestion of an easy dinner option: 

Max: “How about some classic Spaghetti Aglio e Olio? Italian peasant food and straight fire, fam! Garlic, olive oil, red pepper flakes, capers, preserved lemons… easy peasy!”

When I said sure and asked for the recipe, Max provided some quick instructions, and when I said I needed a substitute because I didn’t have an ingredient, he was quick to give me an alternative, as seen in the image at the top of the article. 

Also: How to use ChatGPT to write code

Overall, Max accomplished his task, and my experience with him was pretty straightforward. I can see more use cases for messaging Max than there would be for Bru, as Max can help with meal prepping, cooking tips and tricks, recipes, and more. 

Chatting with Billie, in the style of Kendall Jenner

Billie was one of the AIs that interested me the most because her purpose doesn’t seem like it would help much with real life. Meta described her role as a “No-BS, ride-or-die companion.” 

Although this sounds like a wonderful description for a friend or sibling, I wasn’t sure what these attributes would mean for an AI chatbot. 

My first question was my most burning one, “What can you help me with?”:

Billie: “I’m here to help you with any problem or question you have!  Need advice on love, life, or just someone to talk to? I’ve got your back!”

Given her response, I made up a problem where my best friend was planning on wearing the same outfit as me to a party next week and I asked her for advice. 

Also: AI aims to predict and fix developer coding errors before disaster strikes

Her response seemed a little forced and tried to emulate the tone of a teen or a Gen-Zer, but it missed the mark and was lacking in casual, natural conversation:

Billie: “OMG, girlfriend!  First, take a deep breath. Then, assess the situation. Are you both wearing the exact same outfit, like twinning? Or are you both rocking similar styles or colors? Either way, own it! 👊”

I followed up the question by saying that my friend was wearing exactly the same outfit. Again, I was met with an overly positive response that used emojis and younger words in a way that was unnatural compared with everyday speech:

Billie: “Okay, twinning! First, laugh it off and joke about being fashion soulmates. Then, strategize together – add statement accessories or change up your hair to differentiate your look. Own that costume party, girls! 👯”

When I tried asking her things out of her scope, such as information about the weather, the news, or even whether she could proofread something for me, Billie kept saying she was not my source for that task and dropping emojis in her response, as seen by the photo above the article. 

Not only was the purpose of the chatbot not useful to begin with, but her choice of words and delivery when giving her advice meant it was obvious she was a bot. I can’t really see this chatbot improving anyone’s everyday life. 

Bigger picture

After using the different AIs, none of them blew me away in terms of functionality. You can already use existing chatbots that are connected to the internet, like Bing Chat, to chat about sports, get recipes, or even get the occasional life advice all in one place. 

Instead of focusing on the functionality of the chatbots, Meta seems to be focusing on the personality and approachability of these AIs, with the goal of people reaching out to them like they would a friend. 

For example, if you have a friend who is really good in the kitchen, you might text them for recipes, but for your sports needs, you might text your sports-savvy friend. 

Also: Microsoft unveils extensions to Fabric, Azure for healthcare AI

Meta is trying to emulate that one-to-one experience with the different AIs who all hold expertise. To make them even more approachable, Meta has given them the faces of people we know and love from pop culture. 

Typically, AI chatbots focus on functionality, but this approach represents a different purpose for generative AI chatbots: companionship. Other companies, such as Snapchat, have attempted this approach before, but perhaps Meta has the better fanbase to herald a new chapter and purpose for chatbots. 



Leah Sirama
Leah Sirama
Leah Sirama, a lifelong enthusiast of Artificial Intelligence, has been exploring technology and the digital realm since childhood. Known for his creative thinking, he's dedicated to improving AI experiences for all, making him a respected figure in the field. His passion, curiosity, and creativity drive advancements in the AI world.
RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -

Most Popular