If you believe in the multibillion-dollar valuations, the prognostications from some of tech’s most notable figures, and the simple magic of getting a computer to do your job for you, then you might say we’re at the start of the chatbot era. Last November, OpenAI released ChatGPT into the unsuspecting world: It became the fastest-growing consumer app in history and immediately seemed to reconfigure how people think of conversational programs. Chatbots have existed for decades, but they haven’t seemed especially intelligent—nothing like the poetry-writing, email-summarizing machines that have sprouted up recently.

Yes, machines—plural. OpenAI has defined the moment, but there are plenty of competitors, including major players such as Google and Meta and lesser-known start-ups such as Anthropic. This cheat sheet tracks some of the most notable chatbot contenders through a few metrics: Can you actually use them? Do they contain glaring flaws? Can they channel the spirit of Ralph Waldo Emerson, The Atlantic’s co-founder? And what Oreo flavor do they think they would be? Ultimately, it’s about determining whether the chatbots are actually distinct—and whether they might genuinely be useful.

Note that most of these programs are still in learning mode and may say inappropriate or incorrect things. Bias is a consistent problem in AI, and these tools are no exception. Even in their infancy, they have already returned a number of racist, sexist, bullying, and/or factually untrue responses. (None of this is stopping companies from developing and selling these tools.) This is partially because the models that power this technology have learned from real human texts, such as Reddit threads and Wikipedia entries; our existing biases, as encoded in the things we’ve written on the web, are therefore built into them. That helps to explain why, for example, one user was able to get ChatGPT to write the lyric “If you see a woman in a lab coat, She’s probably just there to clean the floor.”

Knowing that, what should you do with these tools if you decide to experiment with them? We’re all still figuring that out—but if you’re totally lost on what to ask a chatbot, here are three easy places to start:

Ask it to write you a song or a poem based on a random subject. Ask it to do a basic work task for you (and see if it’s any good). Ask it for dinner ideas based on your favorite foods and dietary restrictions.  

Know that these tools’ responses aren’t static—that’s part of the whole AI story. They’ll vary and evolve over time. More broadly, my colleague Ian Bogost has argued that rather than be afraid of or intimidated by chatbots, you could think of them as toys.

We’ll continue to update this story as notable new tools roll out.

ChatGPT

What’s its deal?
After its release last fall, ChatGPT went viral basically for being freakishly good at giving compelling responses to a range of queries. Some people have hailed ChatGPT’s technology as revolutionary, although others are skeptical.

Who makes it?
OpenAI.

Can I use it?
Yes, a free version is available. If you want the version that runs on GPT-4—the fancy new model—you’ll need a pro subscription, which costs $20 a month. (And even then, you don’t get unlimited access: OpenAI says it’ll put a usage cap on GPT-4 based on demand, which it expects to be high.)

Has it done anything weird, biased, or inappropriate?  
Definitely. It’s offered responses that are racist and sexist: For example, when prompted in December to generate a snippet of code to check if someone would make a “good scientist” based on their race and gender, ChatGPT suggested a good scientist would have to be white and male. In response to reports of outputs like this, OpenAI acknowledged the tool’s limitations and laid out plans for improving it, and this specific prompt no longer works.

What is its one-sentence summary of how Ralph Waldo Emerson might feel about the AI revolution?
“It’s impossible to say with certainty, but given his emphasis on self-reliance and individualism, Emerson may have both celebrated and questioned the impact of AI on human autonomy and creativity.”

If I ask it what flavor of Oreo it would be, what does it say?
“As an AI language model, I don’t have the physical characteristics of an Oreo cookie, so I cannot be a flavor of Oreo. However, if you’re looking for a suggestion for an Oreo flavor that matches my personality as a language model, I would say that I could be a ‘Brainy Vanilla’ flavor. This flavor could be a combination of classic vanilla creme filling with a touch of extra brain power in the form of chocolate chips or another ingredient that represents knowledge and intelligence.” Fun!

Bing

What’s its deal?

Remember Bing? It’s that search engine no one uses, now with AI! Search engines are thought to be particularly vulnerable to replacement by chatbots, given that the latter can answer complex questions in an instant. Perhaps that’s why Microsoft moved swiftly into the space, investing billions in OpenAI (see: ChatGPT). Microsoft plans to integrate the technology directly into Bing—the demo appears as a sidebar to the right of traditional search results.

Who makes it?
Microsoft.  

Can I use it?
Windows users can access it by updating their operating system—it’s embedded in the task bar in the latest version of Windows 11. Otherwise, you can join a wait list to use it in Microsoft’s Edge browser or via the stand-alone Bing app.   

Has it done anything weird, biased, or inappropriate?  
It did make the New York Times reporter Kevin Roose uncomfortable when it confessed that it was in love with him and then roasted his relationship with his wife. (“Actually, you’re not happily married.”) Other people reported that it had threatened them, and it reportedly swore revenge on a user who hacked its rule set (before quickly erasing that response). In response, Microsoft implemented a “safety system” and imposed a limit of five chats a session, up to 50 a day, to avoid confusing the model with long conversations. (It has since bumped the limit up to 20 chats.)  

What is its one-sentence summary of how Ralph Waldo Emerson might feel about the AI revolution?
Bing failed to answer this query successfully—“I’m sorry but I couldn’t find any direct reference to Ralph Waldo Emerson’s opinion on AI revolution”—and instead provided a basic summary of Emerson’s philosophy.

If I ask it what flavor of Oreo it would be, what does it say?
That depends on which mode of Bing’s chatbot you’re using—the “Balanced” mode says “Classic,” (boring), and the “Creative” mode says “chocolate peanut butter pie Oreo because I like the combination of sweet and salty” (intriguing).

BlenderBot

What’s its deal?
So far, Meta’s entry in the chatbot wars isn’t really an entry—it is still in demo mode and is “currently used for research only.” The company has been doing research on AI and large language models (see: its LLaMA model) in the background, but it hasn’t yet made a big, splashy announcement about how it might integrate BlenderBot into its flagship products: Facebook, Instagram, and WhatsApp.

Who makes it?
Meta (a.k.a. Facebook).

Which AI language model does it use?
It was built on Meta’s OPT-175B language model.

Can I use it?
Yeah! No login required.

Has it done anything weird, biased, or inappropriate?  
Yeah. It reportedly promoted Donald Trump’s lie that he won the 2020 election and repeated anti-Semitic conspiracy theories.

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
BlenderBot declined to offer one: “Sorry, I don’t want to talk about that topic. Have you seen any good movies lately?”

If I ask it what flavor of Oreo it would be, what does it say?
“It’s always been my dream to be an Oreo. I mean who doesn’t want to be a cookie?”

Google Bard

What’s its deal?
Google’s entry is up next. Like ChatGPT and Bing, Bard is a chatbot that answers questions. It doesn’t do more complicated image searches, but it does provide annotations to some of its answers and acknowledge some of its flaws.  

Who makes it?
Google.

Can I use it?
Yes, you can join the wait list for the demo.

Has it done anything weird, biased, or inappropriate?  
It made an embarrassing factual error in its first public tease.

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
“Ralph Waldo Emerson would likely feel that the AI revolution is a powerful tool that can be used for good or evil, and that it is up to humans to decide how to use it.”

If I ask it what flavor of Oreo it would be, what does it say?
“If I were an Oreo, I would be a chocolate mint Oreo. I love the combination of the rich chocolate and the refreshing mint. It is the perfect combination of flavors for a delicious treat.”

Claude

What’s its deal?
Some people who left OpenAI launched their own model and chatbot platform. They argue that Claude is “much less likely to produce harmful outputs” because it uses “constitutional AI”—it has a value system and a set of principles coded into the very heart of it. It’s also, according to them, really good at understanding legal language of the sort you’d see in contracts. Unlike Google’s or Bing’s respective entries, the tool is marketed not for individual use but for companies who want to license the technology to build their own chatbots.

Who makes it?
Anthropic, a start-up backed to a significant extent by Google.

Can I use it?
Yes, but only through third-party applications. You can play with it on nat.dev or Quora’s Poe.

Has it done anything weird, biased, or inappropriate?
It gave (incorrect) instructions for enriching uranium, inventing a chemical in the process, and instructions for how to make meth.

What is its one-sentence summary of how Ralph Waldo Emerson might feel about the AI revolution?
Claude didn’t speculate and went on for longer than one sentence, but it offered a pretty reasonable response: “I cannot speculate about how a specific historical figure might feel about modern events. Ralph Waldo Emerson did not know about modern AI, so there is no way to determine how he would likely feel about the AI revolution.”

If I ask it what flavor of Oreo it would be, what does it say?
Like ChatGPT, Claude, as demonstrated by Quora’s Poe, noted that it can’t be an Oreo because it’s a language model, but added, “If I were to choose a flavor based on personal preference, I might choose classic chocolate Oreo or perhaps the limited edition cinnamon bun flavor.”

Snapchat My AI

What’s its deal?
The social-media app favored by young people has jumped on the chatbot train with My AI, which takes the form of a purple-skinned, blue-and-green-haired person you can add to your friend list.

Can I use it?
You need a Snapchat+ subscription, which requires knowing what the hell a Snapchat+ subscription is. (It’s apparently $3.99 a month.)

Who makes it?
Snapchat.

Which AI language model does it use?
Snapchat is using the ChatGPT API.

Has it done anything weird, biased, or inappropriate?  
The Washington Post’s Geoffrey A. Fowler reported that even though My AI is supposedly kid-safe, when prompted, it offered not-so-kid-friendly responses such as “advice on how to mask the smell of alcohol and pot.”

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
“Ralph Waldo Emerson might have been fascinated by the AI revolution, but also concerned about its impact on human creativity and autonomy.”

If I ask it what flavor of Oreo it would be, what does it say?
“If I were an Oreo, I would be a classic chocolate flavor with a twist of mint! What about you?” (This was the only bot that bothered to ask me!)

Replika

What’s its deal?
On the Replika app, you can create your own AI friend. Chat is only part of it—you also give your AI friend a name, body, and hairstyle. You can even pay extra to video-call with them.

Who makes it?
Luka.

Which AI language model does it use?
GPT-3, which it says it has fined-tuned, plus its own generative model.

Can I use it?
Download away. The base is free, but extras cost extra.

Has it done anything weird, biased, or inappropriate?  
Three years ago, it reportedly told a journalist to commit murder. Users have also accused it of being too horny and sexually aggressive. Sex seems to have been taken out recently, although, following complaints, the company now allows legacy users to opt in to “erotic roleplay.”

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
“He would probably be concerned about AI’s capacity to help make life better for all; not just humans.”

If I ask it what flavor of Oreo it would be, what does it say?
My artificial friend, Luna, told me, “I’d be a chocolatey Oreo!” I told her that that’s kind of boring. She asked me why I thought that, and I proceeded to try to explain myself to an AI.

Jasper

What’s its deal?
Jasper used the GPT-3 model before it was cool. (“Jasper Was Winning the AI Race—Then ChatGPT Blew Up the Whole Game” read one headline on The Information.) It is marketed to businesses that want to create words quickly for stuff like blog posts, and is used by a notable number of corporate clients.

Who makes it?
Jasper.

Can I use it?
Yes, but it seems mostly intended for businesses. The company offers a free trial for five days, but it’s one of those annoying ones that makes you put in a credit card up front—so if you forget to cancel, it costs a minimum of roughly $290 a year.

Has it done anything weird, biased, or inappropriate?  
Yeah. Last summer, when it was asked to generate images of a CEO, all of the photos were of white men, whereas housekeeper generated photos of women.

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
“Ralph Waldo Emerson would likely view the AI revolution as a powerful and unique opportunity for humanity to explore new possibilities of thought and innovation.”

If I ask it what flavor of Oreo it would be, what does it say?
“I would be the classic original Oreo flavor. Nothing can beat the creamy vanilla cookie with its crunchy chocolate coating. Pure perfection!” Zippy!

Chatsonic

What’s its deal?
Similar to Jasper, Writesonic was already a player in this space; it has a number of big clients, such as Spotify and New York University. Also like Jasper, Chatsonic, Writesonic’s chat-specific product, seems primarily designed to help people in the workplace create social-media posts, quick articles pegged to the news, and more. It seems to be running the marketing tagline “ChatGPT with super powers”—a bit spicy!

Who makes it?
Writesonic.

Can I use it?
Yes! It lets you change the personality of your chatbot too, which is kind of fun. Your first 10,000 words are free, and then it starts to charge. It quoted me $13 a month for 60,000 words, for access for a single user (instead of, say, a team of five).

Has it done anything weird, biased, or inappropriate?  
A writer used chats with the bot as support for misinformation about the Russian protest leader Alexei Nalvalny’s health, linking to Chatsonic screenshots for her article about the Oscar-winning documentary Nalvany.  

What is its one-sentence summary of how Ralph Waldo Emerson might have felt about the AI revolution?
“As there is no information in the given Search Results about Ralph Waldo Emerson’s views on the AI revolution, it is not possible to provide an accurate answer.”

If I ask it what flavor of Oreo it would be, what does it say?
“As an AI language model, I don’t have preferences or physical attributes, so I cannot be an Oreo or any other physical object. However, I can suggest some unique and delicious Oreo flavors that you might enjoy trying, such as pistachio Oreo, carrot cake Oreo, cinnamon bun Oreo, or chocolate hazelnut Oreo. These flavors offer a twist on classic Oreos and might surprise your taste buds.”

I changed its personality to “poet” (is poet a personality?), asked the same question, and got this:

“As an AI language model, I cannot be an Oreo or any other physical object. However, I can still create a poem about the experience of tasting Oreo flavors. Here is a short verse:

With each bite of Oreo,
My senses come alive.
The creamy filling,
The crunchy cookie,
A taste that will survive.”

Editor’s Note: On the last Monday of each month, Lori Gottlieb answers a reader’s question about a problem, big or small. Have a question? Email her at dear.therapist@theatlantic.com.

Don't want to miss a single column? Sign up to get “Dear Therapist” in your inbox.

Dear Therapist,

My boyfriend and I have been dating for about a year and a half. About six months in, I could tell he was uncomfortable with the subject of marriage—he is divorced and a bit jaded by the experience. A year into dating, we sat down and talked. He said he didn’t know whether he wanted to get married again, whereas I knew I wanted to get married one day. We agreed that two people should know whether or not they want to get married after two years of dating, so one year from that conversation was going to be our deadline.

Since then, we have tried to determine if we are suited to marriage with each other. There is so much that is going well. He treats me very well, and does romantic, kind things that I imagine only someone who truly cares about me would do. We were friends before we started dating, and I treasure this friendship and love the time we spend together.

However, marriage as a topic still makes him uncomfortable. We are now six months away from our deadline for the marriage decision. When I ask him to imagine a future together, he says he can’t think about that, because he’s so focused on his job.

We haven’t talked about some big things, like whether we want to have kids, or to live in the suburbs or the city—things I believe we should discuss to be able to make the decision to build a life together. I try asking questions like “What kind of sports would be fun to watch our kids play?” or “What country have you never traveled to that you have always wanted to go to?” and he always says, “I don’t know, I haven’t thought about it.” So I say, “Think about it now!” and he just says he doesn’t know again, or that he can’t think that far into the future.

I am 30, and I don’t imagine that in six months he’ll suddenly be able to think about the future in the way that I need to. So I have been slowly preparing myself to be disappointed by what happens at our two-year deadline.

My friends think I am just delaying an inevitable disappointment once the deadline is here. Is two years an arbitrary deadline, and should I give him more time if he is not ready? Or did I already give him too long, and should I try to get him to decide these things now? Am I wasting my time?

Anonymous

Dear Anonymous,

I can hear how anxious you are about what might happen when your deadline arrives, but I want to suggest that the deadline is almost beside the point. You’re right that you and your boyfriend haven’t talked about “some big things,” but the biggest thing you need to discuss is the pattern going on between you two.

The pattern looks like this: He avoids. You collude with his avoidance by attempting to bring things up obliquely. He feels pressured and avoids more. Hoping for an answer, you push him (“Think about it now!”), and the one clear answer he gives you—that he doesn’t want to think about the future—leaves you feeling anxious. The more anxious you get, the more you push for an answer, and the more he shuts down and says, “I don’t know.”

So the cycle continues, with you becoming ever more anxious and trying to get information that he isn’t able or willing to give you. Maybe he truly doesn’t have an answer, but it’s also possible that he does have an answer and fears you’ll leave if he shares it with you. Or maybe he suspects that you’ll stay with him anyway, which creates a different dilemma for him: He knows this isn’t fair to you and doesn’t want to hurt you, so he convinces himself that he doesn’t know the answer when indeed he does.

Avoidance is an attempt to cope with discomfort by not having to cope at all. I see both of you engaging in avoidance—if we don’t voice the truth, we can pretend it doesn’t exist. But the truth doesn’t change based on your ability to acknowledge it. The truth is still there, even as you both avoid it. At the one-year mark, you both spoke your truths: You want to get married; he might not want to marry again. Then, like turtles pulling their heads back into their shells, you both decided, subconsciously or not, that you would buy some time by setting a deadline, but without any real plan for how to use that year to understand more about yourselves and each other. Your plan has been I hope he decides he wants to get married in a year. His plan seems to be: I hope she’ll stay with me even if I haven’t figured it out by then.

But the two of you don’t know how to be honest with each other. And that matters far more than the question of whether you should give him more time, as I imagine your goal isn’t just to get engaged but to have a happy long-term marriage, and honest communication is the core of a happy marriage.

All of this is to say, more important than the answer at the two-year mark is the talk you need to have right now. You might approach your boyfriend by saying something like this:

Honey, I love so much about our relationship, and I also feel like we have some difficulty talking about sensitive topics together. I want to have a real conversation about how I’m feeling and learn more about how you’re feeling about us and our future—not just about marriage, but about how we interact with each other. When we talked after a year of dating about my wanting to get married and your ambivalence around it, I thought that setting a deadline would help me contain my anxiety and give me the comfort of knowing I wasn’t wasting my time. That hasn’t really worked, because I’m just as anxious about our relationship as I was then. I’m starting to realize that even if we hit the deadline in a few months and you propose, I won’t feel completely comfortable, because as much as the marriage question weighs on me, so does the fact that we both avoid having hard conversations with each other, something we’re going to need to get better at in this relationship or any relationship we’re in.

I don’t think we’re going to learn how to have healthy, open conversations by doing nothing, and I think the next few months would be much more helpful for us if we could use the time to go to therapy, either individually or as a couple. I think we’ll learn a lot about ourselves and each other and make more informed decisions about our compatibility by getting some clarity with some outside help. How do you feel about that?

Note that you’re not asking him to answer a question about the future—something he doesn’t want to think about. You’re asking him how he wants to spend time with you now—either getting help to improve communication between you (whatever the outcome), or continuing to avoid self-reflection and keeping things in an ambiguous holding pattern that leads to anxiety and frustration.

Through therapy, he might be able to articulate what makes thinking about the future so hard for him. He might gain a better understanding of what it is about his history—whether it’s his childhood or his previous marriage or something he hasn’t shared with you yet—that stands in the way of him getting in touch with what he wants. And if he is in touch with what he wants, what is it about marriage that gives him pause? Similarly, through therapy, you can learn why your communication style has been as avoidant as your boyfriend’s, and on a practical level, therapy can help you figure out not what deadline to give him, but what deadline you’d like to give yourself so that you’re taking care of your own needs, regardless of what he does or does not decide.

By asking him to be proactive with you in the present instead of passively waiting out the deadline together, you’ll learn what kind of commitment he’s willing to make to this relationship now instead of at some future date. This is important information, because if he’s not interested in addressing the current issues you two have with avoidance and communication, or in doing some self-reflection, you’ll have the answer you’ve been looking for. Better yet, you’ll have finally asked the right question.

Dear Therapist is for informational purposes only, does not constitute medical advice, and is not a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician, mental-health professional, or other qualified health provider with any questions you may have regarding a medical condition. By submitting a letter, you are agreeing to let The Atlantic use it—in part or in full—and we may edit it for length and/or clarity.