10+ hours of podcasts, in 5 minutes.
8 quotes from 1 episode on Latent Space, each with a timestamped link to the source.
Paul Copplestone argues AI agents require entirely new database architectures to handle automated workloads at scale. Giving every automated process a dedicated cluster will soon exhaust the physical supply of computers.
A code-first local project folder captures all functions and configurations so AI agents can edit database structures as static files.
“This year our big focus is moving to code-first, Git-native. So basically when you launch a Supabase instance inside your local machine you get this Supabase folder and it represents your database. It has all your functions, everything.”
An asynchronous written culture creates a complete historical record that internal AI models read to learn operational context.
“Every single thing that's ever happened in Supabase is documented because we're an async company…”
Allocating a separate Postgres cluster to every automated process is physically impossible at global scale. Current platforms launch 5 million databases monthly but anticipate growing to billions.
“If we give everyone a dedicated Postgres cluster, we'll probably run out of physical computers in the world pretty fast, which is basically what's happening…”
From Why Supabase Acquired Turso to Run Billions of Databases
“At the moment we launch about 5 million databases on our platform every single month…”
From Why Supabase Acquired Turso to Run Billions of Databases
Non-technical builders achieve activation rates near 100% when an agent configures the database in a single step. These users upgrade to paid tiers faster than traditional engineers.
“The sign up to activation, the agent does it for you. Like in one step. So it's basically it's almost 100%. And so those users then were converting to paid at a higher rate than our traditional developer user.”
“SQLite itself is only a single writer. It's a file format…”
From Why Supabase Acquired Turso to Run Billions of Databases
“Imagine putting an agent across a thousand files and asking it, oh, what is the shape of this table? It has to guess through a thousand files.”
“We know that agents are going to operate mostly on code. They don't want to reach out to anything. They've got to iterate very fast on the file system.”
How we attribute quotes. Every quote was matched against the episode transcript, so the words and the timestamp are real (we trim filler words like "um", nothing else). The name comes from our written summary of the episode, and we use it only when a separate check of the captions finds that person on the episode. YouTube gives us no voice-by-voice transcript, so open the timestamp to hear who is talking. See a wrong name? Tell us and we fix or remove it.
10+ hours of podcasts, distilled into one 5-minute read. Free, every Sunday.
For now, every subscriber gets both newsletters. No spam. Unsubscribe with one click.