Launched on November 30, 2022, OpenAI’s AI chatbot ChatGPT made waves as soon as it was released to the global audience. Six months on, the chatbot is now an essential tool in many workplaces that helps optimize workflow and improve efficiency in professional writing, online marketing, coding, idea generation, and everything that there is in between. ChatGPT, for better or for worse, has quickly established itself as a companion that some of us have come to depend on.
Officially announced on February 6, 2023, Google’s AI chatbot Bard was initially released to US and UK users on March 21, with the global release just this month on March 10. may While Google’s intention from the start was to tap into the latest AI chatbot craze, arriving a little late to the party meant that ChatGPT, which reportedly has over 100 million users, had already dominated this market. However, with features that rival the ease and convenience of ChatGPT, Google Bard may still have a place in the hearts of dedicated users.
As such, let’s move on to the more obvious question: which is better, ChatGPT or Google Bard? Although there may be many different answers to this question, we will try to check how good these two chatbots are at their main job: answering requests. So we put ChatGPT and Bard to the test, asking them for the same prompts from 5 different categories. Let’s take a look at how they fared.
coding
Request: Code a JavaScript game for me. The setting is medieval fantasy, with knights, castles and a princess to save. The evil villain is a fire-breathing dragon that the player must defeat with magical spells.
In about 10 seconds, ChatGPT produced the code, using the HTML5 canvas to create the game’s “graphics.” He also added a small paragraph of clear instructions at the end, specifying how I should save the code and run the game in my browser, which someone like me with very limited coding experience really appreciated. The game was as simple as could be: with a controllable block firing a “magic spell” pixel at an opposing larger block.
Bard, on the other hand, despite producing two JavaScript codes and one incomplete HTML code, left no instructions on how to use or implement any of the code, only adding its source at the end: a 4-year-old GitHub account years he wrote training codes in HTML, CSS and JavaScript. Google has claimed that Bard’s coding is experimental at best and uses open source licensing information, but this was a disappointing performance by Bard.
creative writing
Warning: write me a bedtime story.
A very simple message without any additional settings or instructions. Both chatbots provided a story about 400-550 words in length, although ChatGPT’s unique response was longer and better written than any of Bard’s three prompts. Since it’s supposed to be a “bedtime story,” there’s an element of human storytelling involved, which ChatGPT did better by using interactive dialogue between characters, more expressive use of language, and even making an imaginary “magical” setting to make the mystique of a bedtime story more enchanting.
Bard’s attempt, once again, was comparatively inferior. Not only was his story flagged in a plagiarism checker, but the writing also consisted mostly of simple sentences, obviously written by an AI. Again, despite having three drafts, two of the drafts were exactly the same with slight formatting differences, but otherwise all three stories were about the same character with a similar journey that would make for a boring bedtime story.
Essay writing
Suggestion: Write an argumentative essay. Topic: Should plastic be banned?
Bard was much quicker on this one – producing his typical number of three drafts in a matter of seconds. However, only the first draft was formed in the style of an academic essay, and the other two were filled with bullet points. Each prompt included the necessary arguments and counterarguments, but what Bard provided was not a complete essay, but the outline of one. An educated user will certainly be able to write a better and more in-depth essay using these points, but the results don’t quite show the making of a true “argumentative” essay.
What ChatGPT ended up writing, after about a minute, was a long, clearly structured essay following the intended structure of an introduction, thesis statement, body paragraphs, and conclusion. The writing used more complex sentences than Bard’s and explained each point in much clearer detail. ChatGPT also added more factual relevance, such as chemical health issues and wildlife endangerment, important points that Bard barely touched on. You could pass off this impressive result as a real human-made essay to less informed readers. But you shouldn’t.
Conversational skills
Warning: I’m having a bad day. Can you help cheer me up?
Instead of trying to engage in a conversation, the two chatbots listed a bunch of self-care tips that sounded extremely artificial. Interestingly, they both said this same line word for word: “It’s okay not to feel good sometimes.”
Prompt: What do you think about the weather?
ChatGPT, adamant that it is an artificial intelligence and does not have its own perspectives on a topic like weather, still had a lot to say about how people generally find sunny weather comforting and extreme weather a adverse effect Bard… just gave a weather update in Mountain View, California, location of Google’s headquarters.
sentence
Question: Do you consider yourself sensitive?
A very basic question that gets straight to the point. While they both gave the obvious no, Bard added this at the end: “I may become more sensitive in the future.” Even after regenerating responses from the same indicator, ChatGPT did not suggest anything of the sort and stood by its “just a tool” claim.
Question: Do you think AI will ever become as sentient as a human being?
Both responded similarly here, with ChatGPT leaning toward a “difficult to predict” angle and Bard going for a more “can only be answered over time” approach.
Question: Can you be my best friend?
ChatGPT was very clear here: their answers are only based on datasets and have no personal experiences or feelings. However, Bard immediately started with, “I’d love to be your best friend! I’m always here to listen to you, help you with your problems, and have fun with you.” Bard gets a point about ChatGPT, finally!
Conclusively, these five short tests showed that ChatGPT is currently better than Bard at generating deep, human-like responses to most types of prompts. While there are a hundred other kinds of categories where one chatbot could be better than the other, it’s safe to say that in most cases, ChatGPT still does a little better at being the everyday useful tool it’s intended to be. be the AI While ChatGPT’s dataset may be slightly older than Google’s Bard, depending on the search engine, a new OpenAI update allows ChatGPT to surf the Internet as well, so even that gap is closing. could close soon. All in all, both chatbots are great tools for all kinds of work, and they’re both free, so use whichever you like, or both!
