Image by author
The Pathways Language Model (PaLM) has been updated with improved multilingual, reasoning, and coding capabilities. This new model is more capable of understanding and generating text in multiple languages, as well as reasoning and coding.
PaLM 2 was trained on a huge database of text and code in over 100 languages. To improve its logical abilities, developers have included scientific papers and web pages with mathematical expressions. PaLM 2 is also pre-trained on publicly available source code in various programming languages. As a result, it’s a cutting-edge, next-generation language model that powers various Google services.
According to the Google Keynote (Google I/O ’23), Bard is now working on the PaLM 2 model. It is much better at coding, reasoning, and creative writing problems than LaMDA.
Image from Google Keynote (Google I/O ’23)
I have been using the old Bard (LaMDA) for 30 days and the new one (PaLM 2) for 7 days. I’ve seen dramatic changes in how Bard handles coding problems. The bar isn’t perfect, but I think Google is on the right track.
For example, when I asked Bard to create a snake game using Pygame, the old Bard was able to create the game, but it had several bugs and reduced functionality. New Bard managed to create a snake game with all the expected features.
I’m still seeing some bugs with the new Bard, but overall I’m impressed with the progress Google has made.
Image from Bard
I asked both ChatGPT and HuggingChat to generate code to solve a similar problem. ChatGPT produced bug-free code with additional functionality, while HuggingChat produced code with several bugs, missing libraries, and security vulnerabilities.
Image by |: Using ChatGPT
How is Bard different from ChatGPT?
Whenever you write a prompt, it will give you three drafts to choose from. It delivers results quickly and comes with Google services integrations.
To access the drafts, you need to click “view other drafts”.
Image from Bard
To access Google integrations, click the up arrow in the bottom left. It is an answer to the code. You will get the chance to run your code on Google Colab.
Image from Bard
I’ve used Bard for all kinds of data science, from understanding a project to producing high-quality data reports. I think the Bard is the best widescreen model available for the following reasons:
- Grammar and writing. Bard is good at improving grammar and producing realistic text that can be used to improve your writing overall. It’s better than ChatGPT which can be too dramatic.
- Machine Learning Research. Bard is well versed in machine learning topics. It can provide you with accurate information on a wide range of topics, even the latest research.
- Translation: Bard translates well. It can translate between many different languages, including Python code to JavaScript or English to Japanese.
- Brainstorming, Project Planning and Understanding Context. A bard is good at brainstorming, project planning, and understanding context. It will evaluate the chat history to give relevant answers instead of giving random answers.
- Creation of DALL-E 2, Midjourney and Stable Diffusion prompts. The bard is good at creating DALL-E 2, Midjourney and Stable Diffusion prompts. It can help you create realistic images and art from text descriptions.
- Providing links to external sources. Bard is good at providing links to external sources. This can be useful if you want to learn more about a topic or see an example of something Bard has created.
Image from Bard
“I use Bard for everything besides code generation.”
Now let’s talk about the Super Bard that can do it all. In the coming month, Google announced the integration of Google service and third party. That means you can take a prompt in Bard and move the final answer into Google Docs, Colab, Email, or whatever third-party software you use for work.
So far, we know that you can use Bard to perform research, convert it to a spreadsheet, modify the spreadsheet, and export the answer to Google Sheets. Moreover, you can use the Google Lens service to interact with the image. For example, “Can you describe the image in detail?” Similar to GPT-4.
But it is better than GPT-4.
In the future, you’ll be able to use Adobe Firefly to create Images directly from Bard. You’ll be able to automate most of your tasks by simply typing in prompts.
Image by author from Google I/O ’23
In conclusion, I think Bard has the potential to be a one-stop solution for all your work-related problems. The team is constantly working to improve the model and add new features, and they are on track to surpass GPT-4. However, there are still a few areas where Bard can improve, such as the ability to resolve code issues and integration with Google Search. If Bard can solve these problems, I think it will be a truly revolutionary tool that can change the way we work.
Abid Ali Awan (@1abidaliawan:) is a certified data scientist who loves building machine learning models. He currently focuses on content creation and writes technical blogs on machine learning and data science technologies. Abid holds an MSc in Technology Management and a BS in Telecommunications Engineering. His vision is to create an AI product using a graph neural network for students struggling with mental illness.