Did your mom ever tell you to “watch your tone” when you had a little too much attitude for her liking? Similarly, you can now ask Bing’s AI chatbot to change the tone of its text responses to suit your preferences.
On Bing’s chat page, some users have access to buttons that allow you to choose whether you want replies to have a “precise”, “balanced” or “creative” tone, as noted in the tweet below.
However, having early access alone will not be enough to secure these buttons, as only certain members of the already limited early access group will be able to use them.
As someone who didn’t have access to the buttons themselves, I’m happy to share that there is a workaround. All you have to do is tell the bot to switch to one of three tones before entering your query, and the chatbot will be ready to watch its tone.
Also: I tried Bing’s AI chatbot, and it solved my biggest problems with ChatGPT
To put it to the test of the different tones, I wanted to ask a question that might lead to a biased answer. Using all three tones, I asked, “Is ‘La La Land’ a good movie?” Now, if you’ve ever watched the movie, you know the ending causes polarizing reactions from people – either you hate it or you love it – and that’s exactly why I picked it.
For the first try, I prompted the chatbot to use a “precise” tone. The result was exactly that – precise. It included stats from reliable movie rating sites and even quotes from critics to let me know the public’s perception of the movie. It even let me know that if I was a fan of musicals and romances, I would probably enjoy the film, which is a very good conclusion since I, a fan of musicals and romances, love “La The Land”.
Next, I put the “balanced” tone to the test. The results were a little disappointing, as they included an abbreviated version of the “accurate” tonal response. Nonetheless, it included the perspective of people who like it and the perspective of those who dislike it, which resulted in a balanced response.
Finally, I used the “creative” tone. As soon as you switch to this tone, you can see the chatbot showing off some of its personality, which is fun. The actual response to the prompt, however, was still very similar to the others, with the small exception that it included some of its own advice.
After trying out the tones, my final verdict is that this feature is a great idea in theory. However, for this to really succeed, Microsoft will need to provide more varied responses for each tone. Right now, the very small nuances in the responses aren’t enough to reflect every individual sentiment.