Bard vs. ChatGPT: Which One is Better?
Artificial text generators are becoming increasingly popular, with Bard and ChatGPT being two of the most well-known options. But which one is better?
In this video, we put Bard and ChatGPT head-to-head in a series of tasks to see which one comes out ahead. We tested their ability to generate resumes, poems, and code.
Here’s what we found:
- Bard is much faster than ChatGPT. It can generate text much more quickly, which can be a big advantage if you’re on a tight deadline.
- ChatGPT is more thorough than Bard. It provides more details and explanations, which can be helpful if you’re looking for a more comprehensive answer.
- Bard is better at generating code. It can generate working code much more quickly than ChatGPT, and it also allows you to export the code directly to Google Collab.
Overall, we found that Bard is the better option for most tasks. It’s faster, more accurate, and easier to use. However, ChatGPT may be a better choice if you need a more thorough answer or if you need to generate code.
What will the future of artificial intelligence hold?
It’s hard to say for sure, but it’s clear that artificial intelligence is becoming increasingly powerful. As these technologies continue to develop, we can expect to see them used in even more ways.
It’s possible that in the future, artificial text generators like Bard and ChatGPT will be used to create all sorts of content, from news articles to novels to even movies. They could also be used to power new kinds of software and applications.
The possibilities are endless. It’s an exciting time to be alive, and it’s going to be fascinating to see how artificial intelligence evolves in the years to come.
Here are some additional details about Bard and ChatGPT:
- Bard is a large language model from Google AI. It’s trained on a massive dataset of text and code, which allows it to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.
- ChatGPT is a large language model from OpenAI. It’s trained on a dataset of text and code, which allows it to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way.
Both Bard and ChatGPT are still under development, but they’ve already learned to perform many kinds of tasks. As they continue to learn and improve, they’re likely to play an increasingly important role in our lives.
Artificial text generators such as Bard from Google or ChatGPT from OpenAI are amazing but which one is better?Bard or ChatGPT? If you put ChatGPT and Bard against each other in a head-to-head competition, with certain tasks which one would come out ahead? This video is going to pit Bard versus ChatGPT. To get started you can go to Bard from Google or ChatGPT from OpenAI. Click on the try ChatGPT and then just make sure you log in. And then ChatGPT is ready to go.
Then for Bard you do the same thing. You just sign in and once you’re signed in you can see Bard right on the side here. Once you’re signed into Bard and ChatGPT, now it’s time to go ahead and see which one is better. For our prompt we’re going to write a resume. Ao in Bard I’m going to type. So our prompt will be, “Write a resume for a logistics specialist at a delivery company.” We’re going to send this to Bard and we’re going to send this to ChatGPT and we’re going to see who comes out ahead.
So here we have, Bard has made a resume with placeholder name and a summary of a logistics specialist with five plus years experience and then it has the skills that are needed for this, as well as experience in different companies and locations with some bullet points or what to do. As you can see Bard spits this out pretty quick. ChatGPT spits it out line by line and it’s having a bit more detail with this. There’s a lot more bullet points. Maybe too many bullet points for certain ones depending on what you want to have.
Another nice feature about Bard is that you can view other drafts. So here we have draft two and we can see what goes on in draft two and then we can also see draft three so we can see all of those different drafts. Now if we look over at the ChatGPT response on the right, we can see that it has quite a nice resume set out. It has the objectives. Let’s look at the summary. Here is a little bit different so we have a summary of qualifications on both sides, ChatGPT and Bard. I would have to say for this particular prompt I think the output from ChatGPT may be more useful because there are words and phrases you could pull out for your own experience for the resume.
This gives you a lot of nice phrasing that sometimes is the hardest thing to write, rather than on Bard from Google it just wrote these skills. We already know we have these skills. What we want to do is have these skills and a little blurb bullet point on how you actually use those skills. That’s one for ChatGPT.
So let’s go ahead and write a new one. So we’ll have a new competition here. So for this next prompt ,well let’s see, let’s write a poem. So we’re going to write a poem about a butterfly and a calculator and what I’m going to do is. I’m going to send this at the same time so we can see the speed difference because I think that’s where Bard really shines over ChatGPT. Bard is very fast at generating text.
So as you can see, ChatGPT takes off running. Bard just spits it out, and notice we also have three drafts we can go through with a Bard. Bard is very fast. ChatGPT seems to be a bit more thorough but takes a bit longer to generate what is there. This poem is a lot longer, ChatGPT’s poem. We’ll let it go to the end here.So let’s see which one is the better poem. Well this will be up for you the viewer to decide which is the better poem. But for speed Bard is going to spit you out three versions of your prompt much faster than ChatGPT. So for that Bard is the winner. Sometimes for thoroughness, ChatGPT may win there.
Let’s do one more competition. Let’s have it write some code. So for this prompt we’re going to write a Python program that generates cellular automata visually. We’ll go ahead and put this in ChatGPT as well and we’ll click Send.
And ChatGPT is off to the races writing a Python program. And then Bard just pastes a program in. It’s just done. And also we can see the other three drafts of that code and the nice thing about Bard is you can export this to Collab. So you can export your response directly into Collab and then run the code. So that’s something that we can’t do with ChatGPT. ChatGPT does give you some nice explanations, a little bit more explanation about the code that was written than Bard.
One nice thing about the code is, since these large language models are just statistically predicting which word comes next that, you can ask them, “Is this code correct?”
And sometimes they will be honest after they run the whole code back through the system. So here I’m asking, “Is the code correct?”
So here, Chat GPT is apologizing for the incorrect code and is theoretically fixing the code.
By asking Bard to examine the code it has given us a much better explanation of what the code is doing and so that’s a nice feature. As well on the simple tasks, I hope we notice that Bard is much faster than ChatGPT, but ChatGPT seems to be a bit more thorough on certain tasks, especially in the explanations and the text generated.
So here we have this code and we can go ahead and share it into Google Collab. So I’m going to share this response and export to Collab and then open it in Collab. And then we’ll go ahead and run the code, and let’s see what happens. In this particular case I’d say it’s a success. We have cellular automata here shown visually in a code written very quickly in Bard.
So unfortunately, with ChatGPT we have to copy the code, and then we could make a new code box here so we could run the same code. So I’ll just go ahead and paste the code in over top of Bard’s code and let’s see what we get. So now we have a new code and I’m going to click play on the code here and we’ll see. The rule number? This is a nice prompt. I’m going to go with rule 30. Number of generations? Let’s do nine. And the width of each generation? Let’s do four. And I’d have to say that having those prompts is pretty nice feature of the code from ChatGPT.so Even though the Bard code was faster in generating, having these options for input is a pretty nice feature.
So we could just run that again. We can try another rule. We can try rule 24 and then we have number of generations, 600 and then the width of each generation, let’s do eight. So it may need to have some tweaking on the size of the display area but both Bard and ChatGPT were able to generate working code almost instantly.
And the nice thing is you can go back in and ask it to tweak that code and make it more specific and add different things to it as well as debugging your own code. So I’d say that’s a toss-up at the end since both were able to generate but with a slight win towards ChatGPT since it was able to give me prompts and customize the input of the code.
So in this summary of ChatGPT versus Bard, I’d say the competition is pretty even. Each have strengths and pluses and minuses. Bard is much faster and gives you three options as well as being able to upload code instantly to Google Collab. While ChatGPT may be a bit slower but sometimes seems to be a bit more thorough. This will also start to change now that ChatGPT has plugins.
What will the future of artificial intelligence hold? We’ll just have to wait another few weeks.