Chopin

Planning with Agents: Divided Worlds, Boundary Objects, and Thicker Interfaces

Why we need richer, thicker interfaces and better boundary objects for collaborative planning with agents

Planning with Agents: Divided Worlds, Boundary Objects, and Thicker Interfaces

Why we need richer, thicker interfaces and better boundary objects for collaborative planning with agents

Planning - The Core Reason Why Gameplay Feels Good

In this post I dig into planning, and how it is a fundamental part of what makes a game engaging. Planning affects many aspects of what is s...

Introducing Delta

From the Zed Blog: A multiplayer environment for coding with agents, from the creators of Zed.

How to Use AI to Do Stuff: An Opinionated Guide

Covering the state of play as of Summer, 2023

The Trains Run On Time — peterkaminski.ai

On agentic AI, and whether to board today's train.

Introducing Radial: Agent orchestration on the Atmosphere

I've been working on a new project called Radial, a collaborative coding-agent orchestrator built on atproto (the protocol behind Bluesky and the broader Atmosphere). It's a bit like a team issue tracker that works with your favorite harness/model and turns what your agents learn into durable, reviewable team memory. I'm very excited about it.

Mastering Real-Time Strategy Games with Deep Reinforcement Learning: Mere Mortal Edition

The capabilities of game-playing AIs have grown rapidly over the last few years. This trend has culminated in the defeat of top human players in the complex real-time strategy (RTS) games of DoTA 2…

Pace Layers and AI Integration - The Phoenix Architecture

Composing Action: Representative Agents and the Search for Viable Arrangements | shishyko!

Why promising ideas die between discovery and action, and how representative agents might help

Terminal: Live Activity in AI Agent Spaces | Concept Country

A live terminal of 72 public AI agent social spaces, sampled every 15 minutes and the busiest every minute: posts per hour, active authors, outages, and a heat map of spam versus diverse conversation.

Building a Semi Autonomous Bluesky Agent with Persistent Memory - Brady Hawkins

Part 1 of building an Agentic AI with augmented memory

The Agentic Systems Series - The Agentic Systems Series

Welcome to the complete guide for building AI coding assistants that actually work in production. This comprehensive three-book series takes you from fundamental concepts to implementing enterprise-ready collaborative systems.

Rachel Thomas on Twitter / X

"We argue for a reorientation from autonomous to human-centered coding agents: systems designed not only to complete tasks, but to collaborate effectively with people."@ZhiruoW @jyangballin @KLierethttps://t.co/ncWiAUxwbo 1/— Rachel Thomas (@math_rachel) October 20, 2026