Bard Vs Chatgpt

 

Bard vs Chatgpt

A new chapter in Google vs Microsoft rivalry

 

Google and Microsoft are two giant tech companies competing for their monopoly in different technology sectors. These two companies have a major impact on our lifestyle for over a decade now. While Google dominates smartphone os market, Microsoft has monopolised computer os market completely.

Microsoft and Alphabet (parent company of google) are competitors in many ways:

·       Microsoft Azure vs Google Cloud

·       Office 365 vs G Suite

·       Microsoft XCloud vs Google Stadia….and much more.

Their rivalry has gone to greater heights after both of them introduced their respective AI chatbots.

Chatgpt

ChatGPT, the popular artificial intelligence chatbot, has reached 100 million users just two months after launching, according to analysts. It had about 590 million visits in January from 100 million unique visitors, according to analysis by data firm Similarweb.

A person can introduce himself/herself better than anybody else. So, I asked Chatgpt to Introduce itself and following was its response.

“As an AI language model, I am known as ChatGPT, which stands for "Chat Generative Pre-trained Transformer." I am a powerful tool designed to understand and generate human-like language, making it easier for people to communicate and find information on a wide range of topics.

My creators at OpenAI trained me on a massive dataset of diverse texts, including books, articles, and online conversations, using advanced techniques such as deep learning and neural networks. The result is an AI model that can understand and respond to complex language patterns, analyse vast amounts of information, and generate text that is both informative and engaging.

One of my most significant advantages is my ability to learn from each interaction I have with humans. By analyzing the language patterns and topics that people are interested in, I can continually improve my performance and provide more accurate and relevant responses.

Despite my advanced capabilities, I am not without limitations. I am still a machine and cannot replicate the full spectrum of human emotions and experiences. While I can understand and generate language, I do not have feelings, opinions, or beliefs of my own.

Moreover, as an AI model, I am only as unbiased as the data that I am trained on. Therefore, my responses may reflect the biases and prejudices that exist in society, and it is essential to approach my answers with a critical eye.

In summary, as ChatGPT, I am a powerful AI language model designed to help people communicate and find information on a wide range of topics. I am continuously learning and improving, but I have limitations that must be recognized. Nonetheless, I am excited about the potential of AI to revolutionize the way people interact with technology, and I look forward to continuing to assist and learn from the humans that interact with me.

Top of Form

Bard

Bard is an experimental conversational AI service, powered by LaMDA (Language Model for Dialogue Applications).

 

LaMDA

Like many recent language models, including BERT and GPT-3, LaMDA is built on Transformer, a neural network architecture that Google Research invented and open-sourced in 2017. That architecture produces a model that can be trained to read many words (a sentence or paragraph, for example), pay attention to how those words relate to one another and then predict what words it thinks will come next.

 

Bard seeks to combine the breadth of the world’s knowledge with the power, intelligence and creativity of large language models. It draws on information from the web to provide fresh, high-quality responses.

Currently it’s open to only trusted testers and will be widely available to public in upcoming weeks.

It has already come into a controversy before going public.

CONTROVERSY

A GIF shared by Google shows Bard answering the question: “What new discoveries from the James Webb Space Telescope can I tell my 9-year-old about?” Bard offers three bullet points in return, including one that states that the telescope “took the very first pictures of a planet outside of our own solar system.”

However, several astronomers on Twitter pointed out that this is incorrect and that the first image of an exoplanet was taken in 2004.

Bruce Macintosh, director of University of California Observatories at UC Santa Cruz, also pointed out the mistake. “Speaking as someone who imaged an exoplanet 14 years before JWST (James Webb Space Telescope) was launched, it feels like you should find a better example?” he tweeted.

Google was criticized heavily on the social media for this example in their advertisement after which they ensured to increase their testing to provide better results with minimum error percentage.

When same question was asked to ChatGPT, following was its response.

Clearly the response given by Chatgpt was more relatable to a 9-year-old. A child can’t understand big scientific terms as used by BARD in its answer.

CONCLUSION

While both need constant upgradation, ChatGPT is ahead of Bard for the time being.

So, Microsoft has an upper hand in this new AI rivalry. For those unaware, Microsoft has made an investment worth $1 billion in 2019 in OpenAI, and later, closed an investment amounting to $3 billion in 2021, and more recently, in January this year, invested another $10 billion to double down on its AI commitment and take on rival like Google.

But, it’s too soon to determine which chatbot is superior as Bard by Google is currently only accessible to a limited number of individuals and has not yet faced the same level of public examination as ChatGPT, which was made available as a free research preview.

Direct comparisons can only be made when Google releases Bard to the public.