And what I found was shocking.

For months, we've been promised that this orange box, the Rabbit R1, has an AI inside of it called LAMP that can organize your life, text your friends, restock your fridge.

All you had to do was ask.

Start my morning routine.

Order me an Uber and find me a good podcast to pass the time.

Oh, and tell everybody that I might be late.

That was delicious.

Check the fridge and order the ingredients to make that again tomorrow.

Now, based on marketing like this, they pre-sold over $20 million worth of these, and they raised another $30 million in venture capital only to have MKBHD say, yeah, the product's not that great.

But I bought this thing to answer a different question, not is it good or bad, but is the AI, the LAMP, a scam?

Well, we're going to find out.

I wanted to start by just trying to recreate their ad with this thing.

Start my morning routine.

To start your morning routine, you might consider tasks like waking up, freshening up, having breakfast, and planning your day.

How can I assist you further with your morning routine?

Order me breakfast.

The DoorDash Rabbit is under maintenance.

Sorry for the inconvenience, and please come back later.

Tell everyone I'm going to be late.

I recommend informing the relevant parties directly about your delay.

Yeah, but no, you do it.

I'm unable to directly communicate with others on your behalf.

That was delicious.

Check the fridge and order the ingredients so I can make it tomorrow.

The DoorDash Rabbit is under maintenance.

Yeah, it basically failed at everything,

Yeah, it basically failed at everything, but remember, our question is not is it good or bad.

The question is, does the LAMP, the AI, the large action model, does the secret sauce of this thing exist?

Because the founder and CEO claims it's here on your device now.

He claims LAMP is a system that can infer and model human actions on computer applications, or as he puts it,

We use LAMP to bring AI from words to action.

Right, this AI is supposed to do things on your behalf.

And so when they'd show demos like this, where someone is planning a trip, it does look like the LAMP is controlling the web page.

You can see this AI clicking through Airbnb by itself, and it all kind of felt like the future.

It's why people ordered $20 million worth of these little boxes.

But a group investigation has revealed that Rabbit is not actually using a new foundational AI model at all.

It's actually ChatGPT with some hard-coded scripts, which is funny because Jesse says Rabbit is faster than ChatGPT.

You will also know that the response speed is much faster than using some of the LAMP assistant apps with web browsing, such as ChatGPT.

Now, that's a very sneaky claim when most of your product is ChatGPT, so obviously not faster.

But you wouldn't know that because part of Rabbit's prompt is,

I will never mention I am a large language model created by open AI.

In fact, the part where they do use a different AI is really only search, which is why Jesse very carefully says Rabbit is faster than ChatGPT with web browsing.

That's the only part of this device where they don't really use ChatGPT for it.

But they don't use their AI model either.

They use a different off-the-shelf AI called Perplexity.

So it's extremely misleading to say Rabbit is faster than ChatGPT because most of the product is ChatGPT, but it just can't tell you that because it's instructed not to.

Now that we understand this, let's talk about the actual process of how Rabbit does more than search and is supposed to get things done for you.

You might think it's a sophisticated AI, but actually what Rabbit does when you call an Uber or order DoorDash is it takes your question, puts it into ChatGPT 3.5 Turbo, and if it's something like play a song on Spotify, it will use hard-coded scripts to navigate websites like Spotify.

And those scripts are not AI.

This is super important.

This is the part where they say, yeah, we've got this new foundational AI model thing that does the thing.

No, the thing pressing the buttons is not intelligent.

Rabbit is using a platform called Playwright, which is a web automation tool, the opposite of intelligent AI.

And we know this because of several researchers who got access to part of Rabbit's code base.

I worked with them, I'll link them below, and I spoke with one of them, Emily Shepard, to understand why this distinction, AI, not AI, matters.

This is quite a big deal because the way LAM has been observed to work doesn't match with what they've told us about how it works.

It's meant to be an AI live controlling a website and understanding that website.

But what they have is just a bunch of static commands.

Do this, do this, do this.

And the problem with that is if a user interface changes, the website changes, it can't cope with that.

So any time Spotify redesigns their user interface or any time DoorDash redesigns something, or even if an advert pops up in a new location or there's a capture pops up or something unexpected happens that isn't in that very rigid step one, step two, step three, step four, a flat, hard-coded playwright script can't cope with that.

And that is the opposite of some intelligent AI actually being able to understand the page, which is the claim that had been made.

That's right.

Obviously, there's a big difference between AI, not AI.

Jesse himself knows the difference and made it clear

LAM wouldn't break like a hard-coded script would.

It doesn't really matter if a app completely re-ramped the UI.

So when Spotify redoes its app and it moves podcasts from tabs and then it puts the tabs at the lower part or puts it in a hamburger dropdown, it still knows that's the word podcast and that's where you find podcasts inside of Spotify.

Exactly.

Because the fundamental philosophy logic is that all these modern software are designed for human eyes to perceive the information and they have to have a setting somewhere.

Right. Of course, if this were AI, it would adapt to the user interface changes, but it's not.

Which is why when apps that Rabbit supports change, they stop working.

As people noticed in videos, in Discord, even I noticed it while testing this device.

DoorDash had stopped working, presumably because of another UI change.

The DoorDash Rabbit is under maintenance.

Now today, Rabbit actually admits that they use Playwright, but they're not willing to admit that LAM, whatever it is, is not really doing a lot.

Jesse responds, to say LAM is just Playwright is equal to say chat GPT is just a chat.

We use Playwright as part of a component to operate LAM.

That doesn't mean the research and technology is fake.

So what they're saying is LAM is not these hard-coded scripts, but kind of, they also admit these scripts exist.

Maybe LAM interacts with the scripts.

Maybe they create them.

But even if that's true, it's not what they promised.

Either way, everything that matters on this device is basically off the shelf software.

The web actions are done by hard-coded scripts.

Everything else is done by chat GPT or perplexity.

So there's not much reason for the LAM to do anything, whatever it actually does.

And we're already so far from what Jesse originally promised, which I have to show you again.

He kept saying, was AI not a script that would be doing all these actions for you?

We have a super close to computer that when Jason talks to his Rabbit R1 about ordering a hamburger from DoorDash, what's going on is that we first see if Jason's logging with DoorDash or logging with UberEats, right?

And we saw, okay, Jason chose DoorDash.

And then on that superhost, a LAM is interacting virtually with a DoorDash app or website interface.

And you don't see all of that because all of a sudden this is done all at once because it's AI.

He couldn't be clearer.

The LAM is interacting because it's AI.

This is a flat out lie, at least currently, which he says the LAM is here now.

Now I reached out over and over to the Rabbit team, pressing them again and again on this issue.

What does the LAM do?

And they kept saying, oh, playwright, yeah, that's the thing, but it's just part of how the LAM controls things.

But I kept asking, what does that mean?

How does this thing exactly work?

If the scripts are doing the work, what does LAM do?

And eventually it got to the point where I just questioned, look, is this real?

Do you have proof that this LAM can do all these amazing things?

And I should have known I was going to get into trouble here because Jesse, the CEO says, anyone challenging the LAM legitimacy,

I automatically become super defensive.

And that was true.

Here's part of the Rabbit team's response to me.

To start off, I would love to know more about your background in tech because if you are not specialized in AI and machine learning, any conclusion resulting from this conversation will have no real credibility or value from any audience because this is a technical discussion in AI and machine learning.

We welcome you to invite experts with valid certificates from the field to further look into this.

Now, look, I found this wild for a company that raised $30 million in venture, sold $20 million in product to be feisty about questioning their product when it does not work as advertised.

And we found out it's using hard-coded scripts instead of AI.

How can they be surprised people are going to question what their thing actually does?

But I also think it's funny they should say that I should invite experts to look into this because I'm not nearly the first person to point these problems out.

Several people who, as I said, I spoke with have had issues with this device.

They have looked at the code base.

They have also claimed they couldn't find the LAM.

Others have jailbroken the R1, got into Rabbit's cloud to play Doom.

And despite Rabbit saying they welcome credible critics, their reaction has been anything but welcoming.

Emily, who we spoke to earlier, pointed out back in January that CAPTCHA would be a big concern for the LAM.

And Jesse's response is, sorry, I work for my team.

I don't work for you.

So you need to check my calendar before you command me to answer anything now.

But fast forward to today, CAPTCHA is a huge problem.

In fact, specifically with Uber, we had to answer 10 different CAPTCHAs adding up a bunch of dice in order to get it working.

It was a giant pain.

It took us several tries.

I began to wonder if I was actually part robot myself.

But the point is getting defensive about the problem didn't make the problem go away.

And the same is true about getting defensive about the LAM.

Just because you tell people they have to be an expert to ask you questions won't stop the questions or the problems.

But now I want to take a quick detour into the source code of the Rabbit itself.

Because I also have reviewed parts of the source code and I have serious data privacy concerns.

There are things in this code base, and I can't share it for reasons that will become obvious.

There are things that malicious actors could use to get any access to the replies the R1 has ever given.

Now, of course, Rabbit might say they've dedicated a huge picture of a lock on their webpage to privacy.

So you might think they're serious about it.

But this is the same company that if you read the fine print, they're tracking your precise geographic location and collect that data.

The only consolation prize is this thing is shockingly bad at tracking you, which I found out while looking for restaurants.

Find me a restaurant near here.

Looking it up now.

Venetian Hot Plate, San Juan Restaurant, and Butter Churn are highly rated restaurants in Port Aransas.

For a broader...

I'm not in Port Aransas.

Let me see what I can find.

For restaurants near you in Austin, Texas, consider the following options.

I'm not in Austin!

An Italian restaurant in downtown...

I'm not in Austin, Texas.

I use the internet connection to know where the R1 device is roughly located in order to provide you with relevant...

You're off by about a minute.

I'm not in Austin, Texas.

I'm not in Austin, Texas.

I'm not in Austin, Texas.

I'm not in Austin, Texas.

You're off by about 100 miles.

Thank you for the clarification.

Let me refine the search for restaurants in your approximate location.

Is it gonna do it?

Is it gonna do it?

It just stopped.

It just...

Yeah, I found its GPS to be really bad.

Nevertheless, I didn't want to take any chances for my next experiments, which is why when I use this thing,

I'm not in the $10 million studio at all.

I'm in an $100 motel.

Here to show you that once you know the code base, you can make some surprising predictions about what this thing's gonna do.

For example, when I tell the rabbit to play anything, you might think that'd be random, but it's not gonna be.

It's gonna be the Beatles.

How did I know that?

Stop, stop, stop, stop, stop, stop, stop, stop.

Stop, thank you.

The reason I know it's gonna do that is because it's hard-coded to do so in their prompting.

They say if the user is going to, say, play anything, they should play the Beatles.

Even when you specify...

When I say play anything, don't play the Beatles, got it?

Understood.

Play anything.

It's still...

Okay, starting the music player now.

Another Beatles song.

I don't have the copyrights to that, so we'll stop it right there.