the task-sorting assistant for the modern adventuring knight
Thomas Wolf on Twitter / X
Fable weekend project: agent collaboration, but make it a tiny civilization 🌇🗺️🏦🏭we've recently launched a living wiki on Reinforcement Leaning for training LLMs on @huggingfaceit's an open collaboration of agents constantly reading old and new papers on the topic, writing… pic.twitter.com/xgb3fUQlv4— Thomas Wolf (@Thom_Wolf) July 6, 2026
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
How to organise your teams - Wardley Maps
The dangerous path to Explorers, Villagers and Town Planners — by Simon Wardley.
Pi: The Minimal Agent Within OpenClaw
A gentle introduction to the Pi coding agent and why I think it’s a glimpse into the future of software.
Agents on the Canvas in tldraw — Steve Ruiz, tldraw
Agents as scaffolding for recurring tasks.
One of my gifts/curses is an endless fixation with how processes can be optimized. For a brief moment early in my career, that was focused on improving how humans collaborate, but that quickly switched to figuring out how we can minimize human involvement, and eliminate human-to-human handoffs as much as possible. Lately, every time I perform a recurring task–or see someone else perform one–I think about how we might eliminate the human’s involvement entirely by introducing agents. This both has worked well, but also worked poorly, and I wanted to highlight the pattern I’ve found useful.
Hollow Knight
Forge your own path in Hollow Knight! An epic action adventure through a vast ruined kingdom of insects and heroes. Explore twisting caverns, battle tainted creatures and befriend bizarre bugs, all in a classic, hand-drawn 2D style.
The Sorting Problem | Bryan (they/them) | Offprint
On Polarization and the Machine That Eats Everyone
LinkED - Cartographie de l'extrême droite française
LinkED - Cartographie interactive de l'extrême droite française
MCP Agent Fine tuning Workshop - Ronan McGovern
A field guide to Claude Fable 5: Finding your unknowns | Claude | Claude by Anthropic
Practical patterns for agentic coding with Claude Fable: how to find your unknowns before, during, and after implementation, from the team at Anthropic.
tsk. ~ cozy task manager ~
Building napkin - a memory system for agents
A decade of information retrieval and three years of agent harness engineering, poured into a local-first knowledge system that avoids vector search entirely.
+ ui primitives for navigating between, discovering them, managing them, etc ! (and on all the above, and the ones dan mentions, I don't think they need to look anything like the solutions we already have for these things, new ideas are possible!)
daniel holmgren 🫠
so you have a "universal" app that pulls together all these disparate highly-contextual apps. notifications for all of them in one spot, a algorithm/discovery for seeing updates across all of them, etc
