Google Bard's logic and reasoning skills improved with latest update

Google is rolling out two new improvements to Bard to boost its logic and reasoning skills. Firstly, the AI chatbot is improving at mathematical tasks, coding questions and string manipulation, thanks to a new technique called implicit code execution that helps it detect computational prompts and run code in the background.

According to Google, this update combines the capabilities of both Large language models (LLMs) and traditional code to help improve the accuracy of Bard's responses. Through implicit code execution, the chatbot identifies prompts that might benefit from logical code (for instance, "What are the prime factors of 15683615?) - writes it "under the hood," executes it and uses the output to generate a more accurate response.

"So far, we've seen this method improve the accuracy of Bard’s responses to computation-based word and math problems in our internal challenge datasets by approximately 30%," Google said, adding that with these improvements, Bard won’t always get it right - for example, Bard might not generate code to help the prompt response, the code it generates might be wrong or Bard may not include the executed code in its response.

Secondly, Google Bard has a new export action to Google Sheets. This means when the AI chatbot generates a table in its response, you can now export it right to Sheets. 

We’re updating Bard with a new technique called implicit code execution. Now it runs code in the background when it detects computational prompts, improving the accuracy of word and math problems by ~30%.https://t.co/yHayR1VhvT pic.twitter.com/tJzZYjIgIi

— Sundar Pichai (@sundarpichai) June 7, 2023