Experimenting With “Code as Reasoning” in Bing Chat (GPT-4) "Tones" to Solve Mathematical Problems
In this video, I ask Bing Chat (GPT-4) to solve some mathematical problems using an approach similar to "Code as Reasonong" and then trying this out in the 3 different "tones of response" available in Bing Chat. The results were very interesting.
Check out where I first learnet about Code as Reasoning at it applies to a MRKL system, that got me thinking about related prompts I could use in Bing Chat.
https://learnprompting.org/docs/advanced_applications/pal
Here are the list of questions that I asked.
There were nine computers in the server room. Five more computers were installed each day, from Monday to Thursday. How many computers are now in the server room?
Generate Python code to calculate the answer.
Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?
Generate Python code to calculate the answer.
Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?
Generate Python code to calculate the answer.
Emma took a 60 minute plane ride to Seattle. She then took a 2 hour train ride to Portland, and then a 30 minute bus ride to Vancouver. How long did it take her to get to Vancouver?
Generate Python code to calculate the answer.
In this series, you will learn how to use Bing Chat to generate content such as poems, stories, code, essays, songs, celebrity parodies and more. You will also learn how to best create prompts using Knowledge Engineering and an understanding of how foundation models work with finetuning. Check out the features at bing.com