Yandex has started using the YandexGPT language model to create quick responses in Search, the company said. A neural network can list the pros and cons of buying a condo instead of an apartment, list the differences between an alligator and a crocodile, suggest the most affectionate breed of cat, and answer other queries.

Yandex began testing quick responses from the YandexGPT neural network in Search

The neural network gives a short answer to the user’s request in the search bar and summarizes the information from a suitable source, which saves time in searching for information.

At the launch stage, Quick Answers works in limited test mode based on an application in the Yandex with Alice application.

How does it work:

  • YandexGPT finds several suitable sources in real time based on the user’s request.
  • After this, the neural network briefly extracts information from each of them, collecting information even from different parts of the page.
  • YandexGPT then selects the most useful answer from the resulting options and displays it along with a link to the source.

Yandex launched YandexGPT in May 2023. The neural network can create and process texts, retell them, perform tasks, offer new ideas and take into account the context of the conversation with the user.

The company implemented YandexGPT in its Masterpiece application, in sellers’ personal accounts on Yandex.Market, and also began filling product cards on Yandex.Store using a neural network.

On September 7, Yandex released a new version of its neural network: YandexGPT 2. It is capable of solving more different types of problems than the first version and the quality of its answers has also been improved.

Receive the latest news from the world of Web3 in the newsletter. Regularly.
No advertising.

Author:

Anastasia Marina

Source: RB

Previous articleMicrosoft announced an agreement with Oracle to encourage the migration of systems to the cloud
Next articleSon of MCST founder seeks funds to develop new Elbrus-B processor – Kommersant
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.

LEAVE A REPLY

Please enter your comment!
Please enter your name here