Large language models (LLMs) continue to fascinate us with their capabilities to answer our questions, generate presentations and essays for us and many other assorted tasks. These models are also good at generating code for user specified tasks. However, almost all of them do not run the code for us; they simply give us the code that we can copy and execute. Recently, Google has given its large language model, Bard, the computational capabilities as well. Bard thus not only provides the code but also executes it while answering user's questions.
 |
I wanted to check this feature of Bard. Below is what happened when I asked Bard a question that involved some computation.
 |
 |
Google characterizes computing by Bard in response to user questions as "writing code on the fly" method. The company says, "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%." The "writing code on the fly by Bard" is not limited to word or math problems; you can ask Bard to do coding and execution for larger problems too. As an example, I asked Bard to generate and execute code for building a regression model with my data being specified via a URL. I was pleasantly surprised to see Bard execute the code, get the results including the plots. You can read about my this interaction with Bard at this post. |