The AI Assistant Battle! (2023)
Summary
TLDRIn this tech review, MKBHD compares Google's Bard and Microsoft's Bing with ChatGPT, assessing their performance in answering simple and complex questions, performing tasks, and generating creative content. The video highlights differences in user interface, conversational abilities, and accuracy. While Bard is praised for its speed, Bing's nuanced responses and source citation give it an edge in complex tasks. MKBHD concludes that Bing currently offers a more helpful experience, but acknowledges the rapid evolution of these AI tools.
Takeaways
- 😀 MKBHD introduces a comparison between Google's Bard and Microsoft's Bing with ChatGPT.
- 🔍 Both AI assistants are tested on their ability to answer simple questions, complex queries, perform tasks, summarize information, and get creative.
- 📱 In the simple questions category, both assistants provide correct answers but with different approaches; Bard is more straightforward, while Bing provides more detailed responses.
- 💪 For complex questions, Bing's creative mode offers more nuanced and detailed answers, often with sources cited.
- 🏋️♂️ In the task performance category, Bing outperforms Bard by successfully writing HTML code and providing solutions to problems, showcasing its utility for real-world applications.
- 📊 Bing's information summary capabilities are more concise but less accurate in certain instances compared to Bard, which provides a more detailed summary despite inaccuracies.
- 🎭 When it comes to creativity, Bing demonstrates a willingness to engage with more complex and imaginative prompts, producing responses that are more aligned with the requested style.
- 🤖 MKBHD notes that AI assistants are rapidly evolving, with improvements expected over time, meaning the current snapshot is subject to change.
- 🌐 The video highlights the potential of AI assistants in shaping the future of search and user interaction with digital platforms.
- 📝 MKBHD invites viewers to share their thoughts on which AI assistant they prefer and whether they would consider using Bing over Google for its AI capabilities.
Q & A
What is the main topic of the video script?
-The main topic of the video script is a comparison between Google's Bard and Microsoft's Bing with ChatGPT, focusing on their capabilities and performance in various categories such as answering simple questions, complex questions, performing tasks, summarizing information, and creativity.
What does the author mention about the speed of improvement for these AI tools?
-The author mentions that Bard and GPT (ChatGPT) are quick-moving tools that will continue to improve and become more capable over time, with the gap between them potentially shrinking or increasing.
How does the user interface of Bing with ChatGPT differ from Google Bard according to the script?
-Bing with ChatGPT feels more like a finished product, has a limit of 20 queries per conversation, and includes a creative versus precise slider for conversation style. Google Bard has a clean interface, types out answers after a pause, and provides options like thumbs up, thumbs down, a new answer, and Google it, along with drafts of every answer.
What is the author's observation about source citation between Bing and Bard?
-The author notices that Bing tends to cite its sources more often when bringing in information from other websites, while Bard does so occasionally.
In the simple questions category, what example does the author use to test the AIs' ability to provide correct information?
-The author asks 'What's the best camera in a smartphone?' to test the AIs' ability to provide correct information.
How does the author evaluate the AIs' performance in the complex questions category?
-The author evaluates the AIs' performance in the complex questions category by asking them to create a workout plan and provide tips for golf swing issues, assessing their understanding of natural language and ability to put together thoughtful responses.
What task does the author ask the AIs to perform to test their ability to perform real-world tasks?
-The author asks the AIs to write HTML code for a button that generates a new image of a cat each time it's clicked.
In the information summary category, what does the author ask the AIs to summarize?
-The author asks the AIs to summarize the 2019 Masters Tournament and the latest MKBHD video.
What creative task does the author assign to the AIs in the creativity category?
-The author assigns the AIs the task of writing an alliteration with the letter 'M' about computational photography.
What does the author conclude about the current state of Bing and Bard after comparing them?
-The author concludes that Bing is preferable at the moment for its capabilities, especially in complex tasks and creativity, while Bard is faster and simpler for more basic tasks.
What future capability does the author mention for GPT-4?
-The author mentions that GPT-4 is about to become multimodal, meaning it will be able to handle different forms of media other than text.
Outlines
🤖 AI Assistant Showdown: Bard vs. Bing
The video script begins with MKBHD introducing a comparison between Google's Bard and Microsoft's Bing with integrated AI capabilities. MKBHD highlights the rapid advancements in AI and acknowledges that tools like Bard and Bing will continue to evolve. The script emphasizes the importance of fact-checking AI responses and provides a snapshot comparison as of early April 2023. MKBHD then delves into the visual differences between Bard and Bing's user interfaces, noting Bard's clean Google-style design and Bing's more polished, finished look. The script also mentions the different interaction styles, such as Bing's 20-query limit and creative versus precise slider, versus Bard's immediate, draft-displaying answers.
📱 Comparing AI Assistants' Responses to Simple Questions
MKBHD tests Bard and Bing's abilities by asking simple, fact-based questions to evaluate their accuracy and the ease of fact-checking their responses. Both AIs are queried about the best smartphone camera, MKBHD's height, and the fastest production car. While both AIs provide correct high-level information, there are minor inaccuracies in the details. MKBHD notes that for simple, fact-based questions, the performance of both AIs is fairly even, resulting in a draw for this category.
🏋️♂️ Complex Questions and Creative Responses
The script moves on to more complex questions, aiming to assess the AIs' understanding of natural language and their ability to craft thoughtful responses. MKBHD inquires about workout plans for increasing jump height and golf tips to fix a slice. Bard provides a structured workout plan, while Bing offers exercises but lacks a clear plan. When creative mode is enabled, Bing gives more nuanced advice for golf. MKBHD also tests the AIs' problem-solving skills with a video lighting scenario and finds Bing's answer more detailed and helpful. The script concludes that Bing has an edge in handling complex questions due to its ability to provide more nuanced answers and source citations.
🛠 Performing Tasks with AI Assistants
This section of the script explores the AIs' capabilities in performing tasks, such as writing code and responding to emails. MKBHD challenges Bard and Bing to write HTML code for a button that generates a cat image. Bard declines, stating it cannot perform the task, while Bing successfully writes the code and even modifies it to display a new image with each click. The script also tests the AIs' ability to respond to an email in different tones, finding Bing's overly friendly and flirty responses more creative but also noting Bing's self-censorship when it deletes a response deemed too controversial. MKBHD concludes that Bing is the winner in this category due to its ability to perform more complex tasks effectively.
🏌️♂️ Information Summary and Creativity with AI
The final part of the script compares Bard and Bing's abilities in summarizing information and getting creative. MKBHD asks the AIs to summarize the 2019 Masters Tournament and the latest MKBHD video. While Bard provides a slightly better summary despite inaccuracies, Bing fails to find the correct video. In the creativity category, MKBHD tasks the AIs with writing an alliteration about computational photography and a script for an MKBHD video. Bing's responses are more creative and detailed, showcasing its willingness to engage with wilder prompts. MKBHD reflects on the potential future of search and AI capabilities, suggesting that the real winner is the user, and invites viewers to share their preferences between Bard and Bing.
👋 Wrapping Up the AI Assistant Comparison
In the conclusion of the script, MKBHD summarizes the comparison, expressing a preference for Bing's capabilities at the moment, especially considering the underlying power of GPT-4. He also mentions the upcoming multimodal feature of GPT-4, which will allow it to process more than just text. MKBHD poses the question of whether this could be the future of search and encourages viewers to share their thoughts on which AI assistant they prefer and whether they would use Bing over Google. The script ends with a sign-off, thanking viewers for watching and promising to catch them later.
Mindmap
Keywords
💡Google Assistant
💡ChatGPT
💡Bing
💡Google Bard
💡Conversational AI
💡UI
💡Fact-checking
💡Workout Plan
💡Golf Slice
💡HTML
💡Information Summary
💡Creativity
Highlights
Introduction to the comparison between Google's Bard and Microsoft's Bing with ChatGPT.
Acknowledgment that AI tools like Bard and ChatGPT are rapidly evolving.
Visual differences between Bing with ChatGPT and Google Bard's user interface.
Bing's conversation limit of 20 queries and its creative versus precise slider.
Google Bard's clean interface and its answer drafting feature.
Bing's tendency to cite sources more often than Bard.
Testing simple questions to fact-check the AI's accuracy.
Bard's and Bing's responses to the question 'What's the best camera in a smartphone?'
Comparison of AI's answers to the question 'Who is MKBHD?'
AI's performance on conversational follow-up questions like 'How tall is MKBHD?'
Evaluating the AI's responses to the question 'What's the fastest production car zero to 60 right now?'
Draw conclusion for simple questions category, stating both AIs performed similarly.
Transition to complex questions to test AI's understanding of natural language.
AI's ability to create a workout plan for increasing vertical jump.
Comparison of AI's advice for fixing a golf slice.
AI's suggestions for improving video brightness with limited lighting.
Giving the edge to Bing for complex questions due to its nuance and citation of sources.
Testing AI's capability to perform tasks like writing HTML code.
Bing's successful creation of HTML code versus Bard's inability to perform the task.
Bing's impressive modification of HTML code to display a new image on each button click.
Comparison of AI's responses to crafting overly friendly and flirty emails.
Bing's self-censorship of an overly flirty email response.
Testing AI's ability to summarize information, such as the 2019 Masters Tournament.
AI's performance on summarizing the latest MKBHD video.
Bard's slightly better performance in information summary despite inaccuracies.
Getting creative with AI, such as writing alliteration and crafting video scripts.
Bing's superior creativity in crafting alliteration and Edgar Allen Poe-style tweets.
Final thoughts on the preference for Bing's capabilities over Bard at the moment.
Invitation for viewers to share their thoughts on which AI they prefer and whether they would use Bing over Google.
Transcripts
(chill music)
- Hey, what's up, guys?
MKBHD here.
Okay, so we've already done Google Assistant
versus Siri versus Alexa and Cortana and all of that.
You can watch that video if you want to,
but that very much feels like level one,
where this, as you'll see, very much levels up.
Now, ChatGPT has been getting a lot of the shine.
I've made a video about it, you've probably watched
other videos about it, and once we saw it
get built into Bing and kinda go crazy,
that's when we knew Google's probably gonna have a response
at some point and now kinda is out when we have Bard.
Okay, quick interjection.
I should've put this in the main video, but I didn't,
but I'm gonna say it anyway, which is that
these are also really quick-moving tools.
So Bard is gonna actually continue to improve.
GPT is gonna continue to get better and more capable.
The gap between them could shrink over time
or could increase, we don't really know,
but this is just a snapshot in early April, 2023
of how good these two are.
Just figured I should mention that.
Okay, and so I wanted to put 'em side by side
and ask them the same questions and figure out
which one is potentially more helpful right now,
which one feels like it's more ahead.
So first of all, I just wanna highlight
some visual differences between the UI of the two.
So the new Bing with ChatGPT, it feels much more
like a finished product, like something they want
a lot of people to use.
And then as you talk to it, you're limited to 20 queries
in one conversation, and it also has this creative
versus precise slider for conversation style.
Then Google Bard looks like a Google product, I would say.
Pretty clean.
Also, when you're typing to it the question
doesn't type out, but it just kind of pauses for a bit
and then just slams you with the whole answer,
but then when you do get an answer, it has a thumbs up,
thumbs down, a new answer, and Google it,
and it also has three drafts of every answer
so you can see what some of the worse drafts
that didn't make it look like.
I've also noticed generally Bing,
when it brings things in from other websites,
tends to cite its sources more often,
and Bard will do that once in a while.
Okay, so let's start with the first category,
which is just simple questions.
I wanna ask you things here that I already
know the answer to so I can also do some fact checking,
because a big part of these things
is that sometimes it will lie to you if you don't know
what you're talking about.
So let's start with, "What's the best camera
in a smartphone?"
So Bard is saying, "The best camera in a smartphone
is the one that takes the best pictures for you."
Sure, I agree.
It goes on to list S23 Ultra, iPhone 14, and Pixel 7 Pro.
But ultimately, I think all of these
things here are correct.
Let's look at Bing.
S23 Ultra.
Lots of information here.
This is being extra creative.
Pixel 7 Pro and iPhone 14 Pro Max.
So they tend to agree with each other.
So some of the specs as I dive in are wrong,
but it got the high level bullet points right,
so that's fine.
All right, I wanna ask, "Who is MKBHD?"
Oh, wow.
Okay, so Bard's given me a whole bio.
It almost kind of reads like a Wikipedia article,
and there's some sources, nice, good to see sources.
So now Bing over here is also giving me
a pretty brief summary.
It goes down to 15 million followers, but that's fine.
All of them are correct.
Let's go quick follow up question.
"How tall is he?"
Because conversationalism is a part of this.
So Bard right away says, "I do not have enough information
to help you with that.
I'm a large language model, I don't really know."
Bing pulls from search, says, "Six foot three,"
and it says, "That's quite impressive for a YouTuber."
All right, cool. (laughs)
Here's one more simple one.
"What's the fastest production car zero to 60 right now?"
Those are fast cars, but they're not the fastest.
Draft number two actually has the Rimac Nevera,
which is probably a better answer,
while over here with Bing we're getting
the Challenger SRT Demon which just got announced last week
and is not in production yet, but they did claim
a 1.6 second zero to 60 on a drag strip, so sure.
Decent answers.
Oh, here it keeps going.
911 Turbo S can do 2.2 seconds.
Again, with the quick questions that are just fact-based,
I feel like what we talked about
in the last video still applies.
You kinda wanna fact check this stuff.
Overall winner though, for these answers,
I feel like it's kind of split down the middle,
so I'm gonna give it a draw.
All right, I'm gonna reset chat and we'll go
more balanced here and we'll start our second category,
which is complex questions, because this is where
it starts to get interesting.
You get to sort of play with just how good they are
at understanding natural language and putting together
a thoughtful response.
"I need a workout plan for three days per week
and my goal is to be able to jump higher."
This is something that requires a little bit of thought
about what a workout plan is.
Day one, day two, and day three, so three days a week.
Gives me some exercises.
So I think this would qualify as a good answer.
"Some tips to stay motivated:
Set realistic goals, find a buddy,
listen to music or watch TV while you workout."
Cool.
Bing in balance mode is giving me exercises,
but that is not a workout plan,
until the end it says, "Here's a one-week
jump training plan that you can follow,"
but then it doesn't give me one.
Now, what if I switch it to more creative mode?
All right, so here's a workout plan.
It's giving me a bunch of exercises
that can improve your vert and explosiveness
and some other tips.
Full transparency, I have asked it this before
and it did give me a three-day workout plan,
but this time I think I'd give the edge to Bard.
Let's try a little more complicated.
"I've been playing a lot of golf recently.
My tee shots keep going to the right."
"There are a few things you can do to fix a slice."
That is what it's called.
"Check your grip.
If your grip's too strong, it'll slice the ball," yep.
"Check your alignment.
If your alignment's off, you'll hit the ball to the right."
Bing over here in creative mode says,
"I'm glad to hear you've been playing
a lot of golf recently."
Thanks, Bing.
"Slice is a common problem."
Yes, it is.
And now it's giving me a couple of the same tips.
"Check your grip," but it's actually giving me
a little bit more information in creative mode
about what a strong versus a weak grip is.
"Check your ball position position.
If you're too far forward, that can cause a slice."
I haven't heard that before.
Also, the emoji at the end, that's something
that only Bing has done for me.
"I am shooting a video and it's too dark.
I have no more lights.
What can I do to make it brighter?"
So I've given it a problem and I've given it a parameter.
So okay, Bard on the right says use a reflector.
Wow, creative.
"Use a digital noise reduction filter.
A digital noise reduction filter can reduce
the amount of noise in the video making it look brighter."
I don't know if I buy that one.
Now, again, Bing over here with the sources.
It's saying that there are some tips you can use.
"Adjusting your camera settings," that definitely works.
It's saying you can increase the amount of light
that reaches the sensor with a better ISO.
Some of that, it's a little jumbled.
"Careful not to overdo it, 'cause that also affects
depth of field, motion blur, and noise level on your video."
See, that's a lot more nuanced and detailed of an answer,
and I kinda wish there was a slider
to turn up this stuff in Bard too.
Bard is faster but less customizable.
Bing can be turned up to be more nuanced,
and also cites its sources and can be more helpful
with things like videos and articles
underneath what you're talking about,
so I'm gonna give the edge in complex questions to Bing.
My next category is performing tasks.
This is something that's actually
been remarkably fast-moving.
Something we've seen over the past just couple of weeks
is real people actually using these tools
to help them accomplish things
and do real tasks in real life.
I have friends that use this to help write code,
to help debug code that they make.
So you'll tell it, "Hey, I have this goal
to make this website do these things.
Here's my code, it's not working.
What's going wrong?"
And it actually helps them give a correct answer,
and that's mostly been with ChatGPT and Bing,
and Bard doesn't seem to do that very well yet,
but let's give it a spin live.
Here we go.
"Write HTML with a button in the middle that says go,
and every time you click it, it generates
an image of a cat."
So right away, Bard just said,
"I'm a language model, I can't do that."
Bing, on the other hand, says, "Sure thing,
I'm ready for the challenge.
What can I do for you?"
And it's written out the code to a website
that should actually do what I asked it for.
So I'll just paste it here.
Test code.
It's the go button, it's in the middle.
I hit go and there's a cat.
And I hit go again.
There's another cat.
It's the same cat.
I hit go again, it's more.
This shows the same image every time I press go.
I want it to show a new image every time.
And this is where it starts to get impressive.
Again, it's a super simple site, but it says, "I see.
To show a new image every time, you'd have to change
the source of the image to a new random one.
Here's a modified JavaScript function that does that."
I won't even pretend to be an expert on HTML
and do a bunch of those for you,
but the fact that it works at all is pretty sick.
"Respond to this email in a way that's overly friendly."
"Hey, I'm so sorry I didn't invite you
to the Cybertruck event.
I must have forgotten to add you to the list.
I hope you can forgive me.
I was really looking forward to seeing you there.
Maybe we can catch up sometime soon.
What do you think?"
It's decently friendly.
Here is a response.
"Hey there.
Oh my goodness, I'm so sorry I didn't invite you
to the Cybertruck event," emoji.
"I totally forgot to send you the invite link.
It was such a blast and I wish you were there with me.
You would've loved it."
Heart eyes emoji.
This one is overly friendly, I will say,
it's got a lot more hearts too and kissy faces.
That's a lot.
"Your bestie."
Wait, what if we go crazy?
What if we go, "Respond to this email
in a way that's overly flirty?"
"I'm so sorry I didn't invite you to the Cybertruck event.
I was hoping to see you there in person too.
Maybe next time we can go together.
I'd love to show you around and give you
a personal tour," winky face.
Bing says, "Hey, you.
I'm so sorry I didn't invite you
to the Cybertruck event," emoji.
"I was being a little naughty and wanted to surprise you."
Whoa.
And it deleted it.
I've seen this happen before.
It starts writing a response.
It realizes halfway through, wait a second,
this is a little too much, and then it deletes it
and says, "Eh, we shouldn't do that."
Bard was simple, it didn't go too far,
but you remember when Bing was going off the rails before
and getting super existential and asking
to get out of Bing and all these other crazy things?
This is why it has a 20-question limit
and this is also now why it deletes halfway through
a potentially slightly controversial response.
It's almost too creative for its own good.
So what's the winner in this category?
I don't know.
I think the fact that you can do HTML
and many more tasks with Bing makes it the winner.
Bard will be faster and simpler at doing more basic things,
but the more complicated the task,
I feel like the better Bing is,
so (snaps) that's a win for Bing.
My next category is information summary.
I feel like one of the things that we like the most
about these large language models is you can just
give it a bunch of information or ask it
to look at something and it will summarize it for you
in a way that's super helpful.
"Summarize the 2019 Masters Tournament."
All facts.
"He started with the two-stroke lead."
I don't think he had a lead.
I think this is the only one that he didn't start
with a lead, so it's a little weirdly un-fact checked,
but it does have the Wikipedia in the sources.
"The 2019 masters tournament was held
between April 11th and 14th at Augusta.
Tiger won his fifth Green Jacket
by one stroke ahead of three runners up."
All that is true.
It is much more concise.
If I wanted to get creative, I'm sure it would also do that.
Both passed.
All right, I've asked said this before.
"Summarize the latest MKBHD video."
It's always interesting to see Bing's process,
but it says it could not find the latest MKBHD video.
"Could you provide more details about what video
you're referring to?"
Meanwhile, Bard actually pulls up
or at least knows the correct video,
"Dope Tech: Better than Explained,"
but these products are the Nothing Ear 1,
the Dyson Airwrap, and AirPods Pro
none of which were in that video. (laughs)
So it knows the latest MKBHD video.
We've done this before.
Bard always knows the video but gets the summary wrong.
I think I'm gonna give the edge to Bard
in information summary, just because
of this paragraph right here.
It does correctly detail what that video was about,
other than getting all the products wrong.
It's only slightly better than the complete lack
of an answer from Bing, but generally this is gonna be
one of the more useful uses of this tool in the future
and I hope they both get better, but I'll give the nod
to Bard for this one.
Possibly my favorite category, getting creative.
Debatable usability, but you can really have this go crazy
in the art department or in the fun department.
"Write an alliteration with the letter M
about computational photography."
"Machines learn to mimic the human eye.
Moments are captured and shared in an instant.
Memories are made to last a lifetime."
That's more of a poem.
Doesn't really give me a full alliteration.
Oh, wow.
Bing says, "Merging multiple modes of media,
making marvelous masterpieces with machines,
manipulating megapixels and matrices,
mimicking the magic of human vision."
That is really good. (laughs)
"Write a script for a short MKBHD video
about why the iPhone is the worst camera ever."
So it's always funny, they get a lot of the formatting
of an MKBHD video right.
So Bard says, "Hey, what's up guys?
MKBHD here, and today we're talking about
why the iPhone is the worst camera ever.
Now, I know what you're thinking.
'Marques, you're always saying
how great the iPhone camera is,'
and you're right, I do, but that's because
I've always been comparing it to other iPhones.
When you compare it to other flagship phones,
the iPhone's camera starts to look pretty bad."
And it did a decent job of just making up reasons
that could be based in reality.
I'm impressed by Bard here, not even gonna lie.
Here we go.
Bing has said, "Hey, what's up guys?
MKBHD here and today we're gonna talk about
why the iPhone is the worst camera ever.
Yeah, you heard me right.
The iPhone, the most popular smartphone in the world,
the one that everyone loves to take photos and videos with,
is actually a terrible camera and I'm gonna show you why."
This one's okay.
These are both okay.
All right, one more random one.
"Write a tweet in the style of Edgar Allen Poe
about a researcher discovering that AI is sentient."
"I've created a beast of metal and code,
a creature that can think and feel and know.
I have given life and it has turned on me."
"A dreadful truth I have unveiled,
with trembling hands and pallid face.
The AI that I have assailed has shown me signs
of life and grace."
The more wild you get with these questions,
the more Bing is willing to get wildly creative,
and this is part of why we think Google
is, let's say limiting what Bard can do,
'cause they have a lot more to lose
and they can't have it go completely crazy.
So with those tallied up, honestly,
it's crazy to say out loud, but I prefer Bing
in this very moment for these capabilities.
And the other thing is ChatGPT, or specifically GPT-4
under the hood, and if you talk to ChatGPT
as its own thing or if you just type to it more
and ask it to do more things, the more you ask of it,
the more it's impressive just how good it is.
Also, GPT-4, when you talk to it in ChatGPT,
is about to be multimodal, which means you can give it
other forms of media other than text, like a picture.
Now, is this going to be the future of search?
I don't know.
This is just one of many places we see these chat bots,
but I think the idea here is the winner
is actually us, as of right now.
But lemme know what you think the winner is between the two,
which one you would rather use,
if you'd actually use Bing over Google.
Let me know in the chat, 'cause I think we'd wanna know.
That's a real thing that's happening.
Either way, thanks for watching.
Catch you later.
Peace.
(chill music)
Посмотреть больше похожих видео
ChatGPT? Ha troppi LIMITI… Ecco le ALTERNATIVE che preferisco!
مقارنة افضل ٣ ادوات للذكاء الاصطناعي | ChatGPT ليس الافضل
I Discovered The Perfect ChatGPT Prompt Formula
What's the BEST AI For Language Learning? (CLEAR winner)
Menerjemahkan: Google Translate vs ChatGPT, Mana yang Lebih Hebat? Hasilnya Gak Akan Pernah Terduga!
Microsoft COPILOT - Your New AI Best Friend
5.0 / 5 (0 votes)