Bing Chat has made some massive effectivity enhancements and decreased latency points for some queries by 25%. Mikhail Parakhin, the CEO of Bing, stated on Twitter, “yesterday we launched a very reworked backend for internal monologue, decreasing time to first token by ~25%, and, way more importantly, making latency extra secure, decreasing spikes.”
He shared this chart exhibiting the discount:
Michael Schechter from Bing added on Twitter, “These sort of modifications usually don’t make the weblog, however symbolize a ton of labor and a big enchancment to the general expertise.”
Lastly, it appears Bing posted about this enchancment on its weblog submit on Friday, saying, “We shipped efficiency enhancements which have decreased latency spikes for sure chat solutions.”
Discussion board dialogue at Twitter.
