AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Engineering an ML-Powered Developer-First Search Engine with Richard Socher - #582
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Scaling Data Centers
We're using very standard hardware. Bcause we need tho scale. We don't really want to rely on any non standard hardware right now. Even jeepus are often there's a shortage, so we have to sometimes map some of the g pu models and see if we can make em fast enough on a sepiu. Just like spawning out all these machines with a click of a butt, you have a whole new dato center and read use latency for people in a different geo. It's mostly about the people.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode