How the Google Bard is getting better at math and programming: Find out here

Google Bard, the popular ChatGPT competitor, is improving almost daily. Already at the forefront of delivering real-time information, Bard has now added a new export feature to the platform along with capabilities to score better in math and code. Here’s everything you need to know about the platform’s latest developments.

How is the Google Bard improving?

In recent months, Google has dramatically improved Bard’s ability to perform math and coding tasks. These improvements are achieved through a combination of techniques, including:

Hidden code execution: This technique allows Bard to generate code that the computer can execute. This means that Bard can now solve more complex math problems and write more complex code.

blog Google says “A new technique called ‘hidden code execution’ helps Bard detect computer queries and run code in the background. As a result, it can answer math problems, coding questions, and instruct string manipulation more precisely.”

Improved and better inference: As a large language model (LLM), Bard can predict texts, which is useful for creative work, but this means he lack of logical reasoning. That’s why new updates to the platform will help to understand the relationship between different concepts.

It is stated in the official statement “Large language models (LLMs) are like predictors – when they receive a query, they generate a response by predicting which words are likely to appear next. The result is they are exceptionally capable in linguistic and creative tasks, but weaker in areas such as reasoning and mathematics.”

“To help solve more complex problems with advanced logic and reasoning skills, relying on LLM results alone is not enough. Our new approach allows Bard to create and execute code to improve his math and thinking skills.” it added.

See also  You have sharp eyesight if you can spot a frog in the bathroom within 8 seconds!

To test your new abilities, a quick guide “Create a Microsoft Excel sheet about the 10 most populous countries in the world” presented and here is Bard’s response.

“Of course, here’s an Excel spreadsheet for the 10 most populous countries in the world:”

Earth

Population

Change every year

net change

Land Area (Km)

shared world

China

1,444,216,107

0.04%

62.206

9,597,000 won

18.47%

India

1.412,069,323

0.99%

13,586,631

3,287,263

17.70%

USA

332.459,491

0.59%

1,937,734

9,833.520

4.25%

Indonesia

274.221,326

1.07%

2.898.047

1,919,443

3.51%

Pakistan

222.527.818

2.00%

4.327.022

880,940

2.83%

Brazil

213.317,693

0.72%

1,509,890

8,511,699

2.73%

Nigeria

207,301,429

2.58%

5.175,990

910,770

2.64%

Bangladesh

165.848.103

1.01%

1,643.222

130,170

2.11%

Mexico

129,530,753

1.06%

1,357,224

1,943,950 won

1.65%

Bard only generates data for 9 countries, which indicates that the platform is currently incorrect. However, Google warns users about it “Even with these enhancements, Bard doesn’t always get everything right—for example, Bard may not generate code to help with responsiveness, the code Bard generates may be wrong, or Bard may never include the executed code in its response.”

In short, the possibilities of the Google Bard are truly endless. It’s an exciting new technology that has the potential to change the world in many ways. However, the artificial intelligence model still needs a lot of development to give accurate results.

READ| Google Bard: The Final Test

Categories: Trends
Source: vcmp.edu.vn

Leave a Comment