XIMNET - The Leading Tech Agency In Malaysia
A quick look at Google Bard's Gemini Upgrade
On December 6, 2023, Google unveiled Gemini, its newest and most capable artificial intelligence (AI) model. Simultaneously, Bard is updated with Gemini Pro. With Gemini, we can explore amazing new ways to create, interact, and collaborate with Bard.

Let's confirm this by asking Bard directly:


Is Bard powered by Gemini Pro?

What is one way to test a product? By comparing it to its competitors. Let's ask Bard to compare himself with ChatGPT.

Bard vs ChatGPT


One strength of Gemini in Bard is real-time information access, compared to ChatGPT's knowledge, which is cut off in September 2021. Let's confirm this by asking the same question as in our previous ChatGPT article: "Who is the Prime Minister of Malaysia?"

Bard has latest information

A very nice and accurate answer. Let's compare it with other questions.


How to Join in MongoDB

For a technical question like "How to perform a join operation in MongoDB," I prefer Bard's answer since it provides more methods by default. Let's try asking for the code in Python.


Asking for code in Python


For coding questions, both ChatGPT and Bard can provide very good answers. However, Bard is better because it has access to the latest information, which means it can generate code with the latest coding or SDK version updates.

Let's test the language capabilities by asking the same question.

Translation in Bard


For the translation, Bard will break down the phrases without me asking—quite impressive. Additionally, it will provide extra advice based on the context. For example, this sentence is related to health, and it offered some health advice.


Since Bard is now multimodal, lets try it's image capabilities.


About Cat


The answer is quite impressive and detailed. It can even provide information about the cats' situation and details about the location and lighting conditions.


Let's try a more complex question on image


Impressive! Bard managed to find the most expensive drink from the drinks menu photo. 

Let's try a very complex food menu. As a human, I also find this menu quite complicated. You can view the original uploaded image and the result below:

Original food menu


In this situation, the result isn't great, but it's a good beginning for vision capability in LLM models. What apps can we build with this new capabilities? Or how can it be used to improve our CMS?

The Gemini API Vision can offer a range of valuable enhancements for Content Management Systems (CMS) too. Here are some potential applications recommended by Bard:

  • Automatic image tagging and organization: Categorize and tag images based on their content, making them easier to find and manage within the CMS.
  • Content moderation and compliance: Detect inappropriate content within uploaded images automatically, ensuring platform safety and compliance.
  • Image-based search and filtering: Allow users to search for content based on visual elements within images.

Google's Gemini Pro, the latest upgrade for Bard, unleashes a powerhouse of AI capabilities. Compared to competitors like ChatGPT, Bard shines with real-time information access, diverse code generation with the latest updates, impressive language prowess, and even multimodal talents like image analysis and translation. From intricate cat descriptions to finding the priciest drink in a photo, Bard powered by Gemini Pro proves itself a versatile and intuitive AI companion.


XIMNET is a digital solutions provider with two decades of track records specialising in web application development, AI Chatbot and system integration. XIMNET is launching a brand new way of building AI Chatbot with XYAN. Get in touch with us to find out more.
about the article
This article is first published on XIMNET Medium. More resources available here.

XIMNET is one of the leading tech agency for AI Chatbot in Malaysia.

other good reads
Copyright 2024 © XIMNET MALAYSIA SDN BHD (516045-V).  All rights reserved   |  Privacy Policy  |  Get in Touch  |  Employee Code of Conduct  |  Powered by XTOPIA.IO
Ooops!
Generic Popup2