Ben and Ryan chat with Babak Behzad, senior engineering manager at Verkada, about running a pipeline that vectorizes 25,000 images per second into a custom-built vector database. They discuss whether the speed is due to technical brains or brawn, the benefits of processing on device vs. off, and the importance of privacy when using image recognition on frames from a video camera. https://stackoverflow.blog/2025/02/07/why-build-your-own-vector-db-to-process-25-000-images-per-second/
Login to add comment
Other posts in this group
Ryan welcomes Nathan Michael, CTO at Shield AI, to discuss what AI looks like in defense technologies, both technically and ethically. https://stackoverflow.blog/2025/08/22/robots-in-the-skies-and-the
User research for the next era of Stack Overflow https://stackoverflow.blog/2025/08/21/research-roadmap-update-august-2025/
In this episode of Leaders of Code, Stack Overflow CEO Prashanth Chandrasekar and Christina Dacauaziliqua, Senior Learning Specialist at Morgan Stanley, talk about the importance of experiential learn
Senior developers know how to deploy code to systems made of code. Architects know how to deploy ideas to systems made of people. https://stackoverflow.blog/2025/08/20/documents-the-architect-s-progra
Our August release, Stack Overflow for Teams 2025.6, focuses on critical back-end improvements that enhance stability, data integrity, and identity management. https://stackoverflow.blog/2025/08/19/st
Ryan welcomes Evan You, the creator of Vue.js, to explore the origins of Vue.js, the challenges faced during its development, and the project’s growth over a decade. They dive into potential integrati
Wenjing Zhang, VP of Engineering, and Caleb Johnson, Principal Engineer at LinkedIn, sit down with Ryan to discuss how semantic search and AI have transformed LinkedIn’s job search feature. They explo
