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/
Zaloguj się, aby dodać komentarz
Inne posty w tej grupie
An update on recent launches and the upcoming roadmap https://stackoverflow.blog/2025/04/23/community-products-roadmap-update-april-2025/
Ryan chats with Dataiku CEO and cofounder Florian Douetteau about the complexities of the genAI data stack and how his company is orchestrating it. https://stackoverflow.blog/2025/04/22/visually-orch
On today’s episode, Ben and Ryan chat with Laly Bar-Ilan, Chief Scientist at Bit. https://stackoverflow.blog/2025/04/18/generating-components-not-tokens/
Is “agentic AI” just a buzzword, or is it the sea change it seems? https://stackoverflow.blog/2025/04/17/wait-what-is-agentic-ai/
Kyle chats with Jesse Tomchak a software engineer at ClickUp about all the spicy backend takes they could find. https://stackoverflow.blog/2025/04/09/wbit-6-be-curious-ask-questions-and-don-t-argue-w
AI is not a linear process. To scale effectively, engineering leaders must account for varied edge cases, presenting a new set of challenges. https://stackoverflow.blog/2025/04/16/engineering-teams-ne
Kyle interviews Michael Stum, a former Stacker who started (and returned) to answering questions on the community site. https://stackoverflow.blog/2025/04/16/wbit-7-exploring-webassembly-with-the-fir
