~/blog
$
~/recent
>
#ai#memory#architecture
Memory Like a Brain
I've been building an AI agent for the past few months, and somewhere along the way I realized I was accidentally recreating a brain.
>
#ai#agents#ux
Mid-Turn: What Happens When You Interrupt an Agent
Most agent systems treat turns as atomic. Except that's not how anyone actually uses these things.
>
#ai#agents#architecture
One Main Thread
The trick to building an agent that keeps up with you turned out to be counterintuitive: give the main agent fewer tools, not more.
↑↓ navigate · enter to read