Topics
Latest
AI
Amazon
Image Credits:Jaap Arriens / NurPhoto(opens in a new window)/ Getty Images
Apps
Biotech & Health
clime
Image Credits:Bing
Cloud Computing
Commerce
Crypto
Enterprise
EVs
Fintech
fund raise
Gadgets
Gaming
Government & Policy
Hardware
layoff
Media & Entertainment
Meta
Microsoft
Privacy
Robotics
security department
societal
infinite
inauguration
TikTok
Transportation
Venture
More from TechCrunch
consequence
Startup Battlefield
StrictlyVC
Podcasts
picture
Partner Content
TechCrunch Brand Studio
Crunchboard
Contact Us
Microsoft Bing is getting a new “ Deep Search ” feature powered by OpenAI ’s GPT-4 . The feature is plan to give exploiter more relevant and comprehensive answers to complex lookup enquiry . Microsoft notes that Deep Search is not a replacement for Bing ’s existing web hunt , and is rather an enhancement that allows for deeper geographic expedition of the web .
In ablog post , Microsoft excuse that the new feature work up on Bing ’s current web index and ranking system and enhances them with GPT-4 , which takes the hunting query and change state it into a more comprehensive verbal description of what the results should include .
For instance , say a user is looking into loyalty programs in different countries and enters the query : “ how do points systems work in Japan . ” Deep Search would take the query and flourish it into the following :
cater an account of how various loyalty card plan work in Japan , admit the benefit , necessity , and limitations of each . Include examples of popular loyalty posting from different category , such as wash room stores , supermarket , and restaurants . Show a comparison of the advantage and disadvantages of using commitment cards versus other defrayment method in Japan , including current reward and benefits . foreground the most popular services and enter merchants .
With this expanded verbal description , you are able to explain your purpose well than you could with just a few words .
In instance where your search enquiry is more ambiguous , Deep Search will find all of the possible intents and creates a comprehensive verbal description for each of them . Deep Search then expose these intent to you , allowing you to take the right one .
Once the expanded description has been created , Bing will pull relevant result that often do n’t show up in typical search results , Microsoft says . Deep Search finds Page that might match the expand query , rewrites the query and then searches for those variations too .
Join us at TechCrunch Sessions: AI
Exhibit at TechCrunch Sessions: AI
Sticking with the same trueness tip query case above , Deep Search may also explore for thing like “ loyalty card programs Japan , ” “ best allegiance cards for traveler in Japan , ” “ comparing of loyalty programme by class in Japan , ” “ redeeming loyalty cards in Japan ” and “ managing loyalty points withe speech sound apps . ”
“ By doing this , Deep Search can line up results that cover different aspects of my query , even if they do n’t explicitly include the original keywords , ” Microsoft wrote in the web log post . “ even search on Bing already deliberate billion of vane page for each hunt and Deep Search does ten times that to find results that are more informative and specific than the single that place higher in normal search . ”
Once Deep Search has collected web pages , it range them based on how well they match the expanded verbal description . When ranking , Deep Search considers how well the topic pit the interrogation , whether it has an appropriate level of details , how trustworthy the Sir Frederick Handley Page is and how Modern and popular it is .
Microsoft observe that Deep Search is optional and can take up to 30 minute to complete , which is why it ’s not meant for every query or user . For substance abuser who do n’t want more comprehensive reply , they can get unconstipated Bing lookup results instantly .
Microsoft Bing to arrive at more personalized answer , support for DALLE - tocopherol 3 and watermarked AI paradigm
