Bing Chat Improves Efficiency & Reduces Latency Issues By 25%

Jul 3, 2023 - 7:31 am 1 by
Filed Under Bing Search

Fast Happy Bing Robot

Bing Chat has made some big efficiency improvements and reduced latency issues for some queries by 25%. Mikhail Parakhin, the CEO of Bing, said on Twitter, "yesterday we released a completely reworked backend for inner monologue, reducing time to first token by ~25%, and, far more importantly, making latency more stable, reducing spikes."

He shared this chart showing the reduction:

click for full size

Michael Schechter from Bing added on Twitter, "These type of changes often don’t make the blog, but represent a ton of work and a significant improvement to the overall experience."

Finally, it seems Bing posted about this improvement on its blog post on Friday, saying, "We shipped performance improvements that have reduced latency spikes for certain chat answers."

Forum discussion at Twitter.

 

Popular Categories

The Pulse of the search community

Search Video Recaps

 
Video Details More Videos Subscribe to Videos

Most Recent Articles

Search Forum Recap

Daily Search Forum Recap: July 3, 2025

Jul 3, 2025 - 10:00 am
Google Ads

New Google Ads AI Max Search Match Type

Jul 3, 2025 - 7:51 am
Google Ads

Google Ads Top Stop Serving Message Assets With Unverified Phone Numbers

Jul 3, 2025 - 7:41 am
Google

Similarweb: No Clicks From Google Grew From 56% to 69% Since AI Overviews

Jul 3, 2025 - 7:31 am
Google

Report: Over 12% Of People Also Ask Results Are Google AI Overviews

Jul 3, 2025 - 7:21 am
Google Maps

Google Tests Local Panel Tab Buttons Under Main Search Bar

Jul 3, 2025 - 7:11 am
Previous Story: Google Analytics UA 3 Still Collecting Data But Google Says Not For Long...