[Global] Microsoft will set limits for conversations with Bing chatbot

Microsoft intends to start limiting conversations with the new chatbot in its Bing search engine to five questions per session and 50 questions per day, The New York Times reports.

The company announced the change in a blog on February 17.

Microsoft publicly released a new version of Bing at an event on its Redmond, Washington, campus a fortnight ago. It combines the search engine with artificial intelligence technology built by OpenAI, a San Francisco start-up

A number of other tech giants - including Google - are reportedly working on similar services. However, Microsoft has moved swiftly to gain a technological advantage over its competitors with the company promising that AI will eventually be integrated into a wide range of its products.

Microsoft had expected its chatbot to respond inaccurately at times and had built-in measures to protect against people who try to make the chatbot behave strangely or say harmful things. Nevertheless, early users engaging in open-ended, personal conversations with the chatbot found its responses unusual and occasionally creepy.

After the change, users will reportedly be prompted to begin a new session after they ask five questions and the chatbot answers five times.

“Very long chat sessions can confuse the underlying chat model,” Microsoft said on February 17.

Earlier this week the company wrote, in a blog post, that it “didn’t fully envision” people using the chatbot “for more general discovery of the world, and for social entertainment.” It said the chatbot became repetitive and, sometimes, ‘testy’ in long conversations.

Source: The New York Times

(Links and quotes via original reporting)

Microsoft intends to start limiting conversations with the new chatbot in its Bing search engine to five questions per session and 50 questions per day, The New York Times reports.

The company announced the change in a blog on February 17.

Microsoft publicly released a new version of Bing at an event on its Redmond, Washington, campus a fortnight ago. It combines the search engine with artificial intelligence technology built by OpenAI, a San Francisco start-up

A number of other tech giants - including Google - are reportedly working on similar services. However, Microsoft has moved swiftly to gain a technological advantage over its competitors with the company promising that AI will eventually be integrated into a wide range of its products.

Microsoft had expected its chatbot to respond inaccurately at times and had built-in measures to protect against people who try to make the chatbot behave strangely or say harmful things. Nevertheless, early users engaging in open-ended, personal conversations with the chatbot found its responses unusual and occasionally creepy.

After the change, users will reportedly be prompted to begin a new session after they ask five questions and the chatbot answers five times.

“Very long chat sessions can confuse the underlying chat model,” Microsoft said on February 17.

Earlier this week the company wrote, in a blog post, that it “didn’t fully envision” people using the chatbot “for more general discovery of the world, and for social entertainment.” It said the chatbot became repetitive and, sometimes, ‘testy’ in long conversations.

Source: The New York Times

(Links and quotes via original reporting)