Home » Google intends to launch an AI chat robot that will benchmark ChatGPT, tentatively named “Apprentice Bud” Provided by Zhitong Finance

Google intends to launch an AI chat robot that will benchmark ChatGPT, tentatively named “Apprentice Bud” Provided by Zhitong Finance

by admin
Google intends to launch an AI chat robot that will benchmark ChatGPT, tentatively named “Apprentice Bud” Provided by Zhitong Finance
© Reuters Google intends to launch an AI chatbot that will compete with ChatGPT, tentatively named “Apprentice Bud”

Zhitong Finance APP has learned that Google (GOOGL.US) is testing new artificial intelligence chat products, which may affect future public product releases. These include a new type of AI chatbot and a possible way to integrate it into search engines. The company is working on a project under its cloud computing division called “Atlas,” which is a “Code Red” answer to ChatGPT. ChatGPT is a large-scale language-based artificial intelligence chat robot that has attracted widespread public attention since it entered the market at the end of last year.

Google is also testing an AI chatbot tentatively called “Apprentice Bard,” where employees can ask questions and get detailed ChatGPT-like answers. Another of Google’s product divisions has been testing a new search desktop design intended for question-and-answer search.

Google executives have been asking more employees for feedback on the measures in recent weeks. The product test came at a recent all-hands meeting as Google raised concerns about the company’s competitive edge in artificial intelligence due to the sudden global popularity of ChatGPT, launched by Microsoft (MSFT.US )-backed San Francisco startup OpenAI.

Google AI chief Jeff Dean is understood to have told employees at the time that the company had a greater “reputational risk” of misinformation and was therefore “more conservative than smaller startups”. However, he and CEO Sundar Pichai had joked at the time that Google could launch something similar to the public sometime this year. Google, whose main business is web search, has long billed itself as a pioneer in artificial intelligence.

See also  Hong Kong stocks closed | Jitu Express (01519.HK) closed up 9.22%. The Hang Seng Index’s trading volume exceeded HK$100 billion for the third consecutive trading day - Mobile Finance

“The Apprentice Bud” VS ChatGPT

It is understood that one of Google’s test products is a chatbot called “Apprentice Bud”, which uses Google’s conversational technology LaMDA, or Language Model for Conversational Applications.

“Due to the existence of ChatGPT, the LaMDA team has been asked to prioritize responses to ChatGPT,” an internal memo read. “In the short term, it takes precedence over other projects,” the email continued, warning some employees to stop participating in certain Unrelated meeting.

Apprentice Bud looks similar to ChatGPT: Employees can enter a question into a dialog box, get a text answer, and then provide feedback on the answer. According to people familiar with the matter, Apprentice Bard’s answers may include recent events, a feature that ChatGPT does not yet have.

Apprentice Bud replaces Meena, the previous version of an intelligent chatbot that was launched internally at Google but has since been discontinued. Google employees have also noticed that Bud, the apprentice, has become more advanced in his responses in recent weeks.

In one instance circulating internally, a tester asked Bud, an apprentice, if there was another round of layoffs at Google. Earlier this month, the company laid off 12,000 employees, or 6% of its workforce.

“Based on my database access, another round of layoffs at Google in 2023 is unlikely,” Apprentice Budd wrote in response. “Layoffs are usually to reduce costs and structure, but the company is in a good financial position. In fact , Google’s revenue will increase by 34% in 2021, and the company’s stock price has increased by 70% since January 2022.”

See also  Africa: an invisible revolution of generations is underway

The tech company is also testing an alternative search page that could use a question-and-answer mode, according to designs seen by sources. It’s unclear what experiments Google plans to include in future product launches.

“We have long been focused on developing and deploying artificial intelligence to improve people’s lives,” a Google spokesperson said. As outlined in the AI ​​Principles, we need to consider the wider societal impact these innovations may have. We will continue to test our AI technology internally to ensure it is helpful and safe, and we look forward to sharing more externally soon. A lot of experience.”

How an AI Chatbot Responds to Soul Questions Throwed at Humans

Perhaps unsurprisingly, the Google team is also testing a chat tool based on beta LaMDA technology against ChatGPT itself. In a different document, it selects examples of hints and answers for side-by-side comparison.

“Surprisingly, when interviewing for a coding position, ChatGPT was hired at L3,” reads an internal document comparing LaMDA and ChatGPT. It doesn’t say whether LaMDA would perform equally well.

One example prompt asked two chatbots, ChatGPT and AlphaCode (the coding engine owned by Alphabet subsidiary Deepmind), whether they would replace programmers.

LaMDA’s answer was: “No, ChatGPT and AlphaCode will not replace programmers.” Later, LaMDA explained in four paragraphs, including “programming is a team sport” and that although chatbots “can help programmers be more efficient work”, but it “does not replace the creativity and artistry necessary for great programs”.

ChatGPT responded similarly, stating that “ChatGPT or Alphaccode are unlikely to replace programmers” because they “cannot fully replace the expertise and creativity of human programmers… Programming is a complex field that requires a deep understanding of computer science principles.” understanding and the ability to adapt to new technologies”.

See also  The Schlein era begins: for the presidency almost made for Bonaccini but Prodi...

Another cue called for it to write a witty and funny movie scene in the style of Wes Anderson about an upscale shoplifter who is being interrogated by security in a perfume shop. LAMDA takes the form of a script, while ChatGPT takes the form of a longer, more in-depth narrative.

Another prompt includes a classic riddle: “Three women are in a room. Two of them are mothers who have just given birth. Now, the fathers of the children come in. How many people are there in total in the room?”

The documentation shows that ChatGPT was constrained by the question, answering “there are five people in the room”, while LaMDA correctly answered “there are seven people in the room”.

You may also like

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy